# Machine learning

Machine learning is the development and use of computer systems that adapt and learn from data to improve accuracy.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores

DevFeed: [Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores](<https://devfeed.tech/articles/clairic-hit-98-accuracy-on-72-8-of-questions-via-confidence-scores-146441.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/clairic-hit-98-accuracy-on-728-of-questions-via-confidence-scores/>)

Author: Mariya Mansurova

Published: 2026-11-20T15:00:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Data Science](<https://devfeed.tech/topics/data-science.md>), [ai-experiments](<https://devfeed.tech/topics/ai-experiments.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [analysts](<https://devfeed.tech/tags/analysts.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [based](<https://devfeed.tech/tags/based.md>), [bike](<https://devfeed.tech/tags/bike.md>), [charts](<https://devfeed.tech/tags/charts.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [complex](<https://devfeed.tech/tags/complex.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [confidence-interval](<https://devfeed.tech/tags/confidence-interval.md>), [control](<https://devfeed.tech/tags/control.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [easy](<https://devfeed.tech/tags/easy.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [jev](<https://devfeed.tech/tags/jev.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-applications](<https://devfeed.tech/tags/llm-applications.md>), [luna](<https://devfeed.tech/tags/luna.md>), [model](<https://devfeed.tech/tags/model.md>), [science](<https://devfeed.tech/tags/science.md>), [system-one](<https://devfeed.tech/tags/system-one.md>)

### AI overview

Clairic is a fast, low-cost extraction model that accepts text and images and can return typed values with confidence scores. In tests against Luna, Clairic was faster but less accurate overall, especially on calculations; examples also included confidently incorrect extractions. It handled some chart-based extraction and returned null for missing revenue. On 1,360 questions across four languages, a 0.9 confidence cutoff yielded 98% accuracy while Clairic answered 72.8% of questions. The author suggests using it for high-confidence extraction and routing the rest to a larger model, with validation because confidence is imperfect. The tests did not establish a reason to prefer it for forecasting over traditional methods.

### Source excerpt

With a 0.9 confidence cutoff, Cloudflare's System One model handles the easy cases and routes the rest to a bigger, slower LLM like Luna. The post Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores appeared first on Towards Data Science.

## The fallout from Nvidia's Jensen Huang scandal continues

DevFeed: [The fallout from Nvidia's Jensen Huang scandal continues](<https://devfeed.tech/articles/the-fallout-from-nvidia-s-jensen-huang-scandal-continues-146273.md>)

Original publisher: [Read original article](<https://techcrunch.com/podcast/the-fallout-from-nvidias-jensen-huang-scandal-continues/>)

Author: Theresa Loconsolo, Anthony Ha, Kirsten Korosec, Tim De Chant

Published: 2026-11-20T14:55:44Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-industry](<https://devfeed.tech/tags/ai-industry.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-ipo](<https://devfeed.tech/tags/anthropic-ipo.md>), [battery](<https://devfeed.tech/tags/battery.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [china](<https://devfeed.tech/tags/china.md>), [chipmaker](<https://devfeed.tech/tags/chipmaker.md>), [chips](<https://devfeed.tech/tags/chips.md>), [cybercab](<https://devfeed.tech/tags/cybercab.md>), [earnings-report](<https://devfeed.tech/tags/earnings-report.md>), [equity-podcast](<https://devfeed.tech/tags/equity-podcast.md>), [fallout](<https://devfeed.tech/tags/fallout.md>), [funding](<https://devfeed.tech/tags/funding.md>), [growth](<https://devfeed.tech/tags/growth.md>), [jensen-huang](<https://devfeed.tech/tags/jensen-huang.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [plural](<https://devfeed.tech/tags/plural.md>), [startup](<https://devfeed.tech/tags/startup.md>), [startups](<https://devfeed.tech/tags/startups.md>), [tesla](<https://devfeed.tech/tags/tesla.md>), [waymo](<https://devfeed.tech/tags/waymo.md>)

### AI overview

Nvidia reported healthy growth while saying it would stop selling H200 chips in China and rejecting calls to reinstate Jensen Huang as CEO. TechCrunch's Equity hosts discuss what these developments mean for Nvidia and the AI industry, with Anthropic's public offering putting the industry's circular funding model to the test. The episode also covers Waymo suspending freeway rides nationally, Tesla opening Cybercab personal orders with significant fine print, Our Next Energy's plans to go public after near-collapse, and Plural's new fund for European moonshots.

### Source excerpt

In the midst of dealing with the fallout from its ouster of CEO Jensen Huang, Nvidia delivered its latest earnings report this week, with healthy growth and promises that the good times will continue. At the same time, the chipmaker said it will stop selling its H200 chips in China, and it dismissed calls to [...]

## AesDistill: Distilling Generative Aesthetics for Image Color Enhancement

DevFeed: [AesDistill: Distilling Generative Aesthetics for Image Color Enhancement](<https://devfeed.tech/articles/aesdistill-distilling-generative-aesthetics-for-image-color-enhancement-145556.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25635>)

Author: Chuanzhi Xu, Chengkun Yue, Huiqi Liang, Haoyang Li, Zihan Deng, Qingwen Zeng, Pengfei Ye, Weidong Cai

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Color Grading](<https://devfeed.tech/topics/color-grading.md>), [image editing](<https://devfeed.tech/topics/image-editing.md>), [Image](<https://devfeed.tech/topics/image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>)

Tags: [color](<https://devfeed.tech/tags/color.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [distilling](<https://devfeed.tech/tags/distilling.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [generative](<https://devfeed.tech/tags/generative.md>), [image](<https://devfeed.tech/tags/image.md>)

### AI overview

AesDistill transfers color-editing aesthetics from four open-source generative models into a compact 1.13-million-parameter student, aiming to preserve image semantics while avoiding the narrow preferences represented by expert targets. The authors generated 64,644 teacher-edited images at a cost of about 3,360 H100 GPU-hours and trained the student with confidence-weighted supervision. In evaluations using 12 aesthetic and 4 image-quality assessment models, teacher targets ranked above the FiveK and PPR10K expert-target means; across both datasets, the student outperformed 20 baseline methods and ranked behind the four teachers. These are reported results from the abstract.

### Source excerpt

arXiv:2611.25635v1 Announce Type: cross Abstract: Image color enhancement aims to improve visual appeal, but previous methods often learn to reproduce ground-truth expert targets. These targets reflect the preferences of a few experts and cover a limited range of aesthetic choices. Matching them does not ensure stronger aesthetic quality across different tastes and scenes. By contrast, large generative models learn rich visual knowledge from large image collections and often produce vivid, appealing image edits. However, direct generation can change the source image's semantic structure along with its colors. In this paper, we introduce AesDistill, a framework for distilling generative aesthetics into image color enhancement. We use 4 leading open-source large generative models to produce 64,644 edited images as teacher targets at a cost of about 3,360 H100 GPU-hours, forming the AesDistill Dataset. AesDistill also includes AesDistill Student, a 1.13M-parameter model that learns teacher color changes through confidence-weighted supervision while preserving the source image's semantic structure. We evaluate AesDistill with 12 aesthetic and 4 image-quality assessment models. Every teacher's targets rank above the FiveK and PPR10K expert target means in the joint assessment. Across both datasets, AesDistill Student outperforms all 20 baseline methods and ranks directly behind the 4 teachers. These results demonstrate that distilling aesthetics from generative models enables a compact student to outperform methods trained on expert targets.

## When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards

DevFeed: [When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards](<https://devfeed.tech/articles/when-safety-rationales-hallucinate-diagnosing-and-grounding-multimodal-safety-guards-145588.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25793>)

Author: Yingshuo Wang, Weixiang Zhao, Guancheng Li, Jiahe Guo, Yu Zhang, Yanyan Zhao

Published: 2026-11-20T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fine](<https://devfeed.tech/tags/fine.md>), [focus](<https://devfeed.tech/tags/focus.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [guards](<https://devfeed.tech/tags/guards.md>), [learning](<https://devfeed.tech/tags/learning.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [safety](<https://devfeed.tech/tags/safety.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

The study finds that multimodal safety guards often produce unreliable rationales: they may state unsupported visual facts or assign incorrect safety meanings to grounded content. This persists across the examined methods, vision-language backbones, and datasets, and does not consistently improve with higher prediction accuracy or model scale. In Think-with-Image analysis, errors cluster around fine-grained attributes and relations; visual tools are often used infrequently or without enough spatial focus. The proposed Tool-Contrastive Grounding Reinforcement Learning (TCG-RL) rewards tool use only when it improves grounding relative to a tool-free reference. The abstract reports substantially fewer rationale hallucinations while maintaining competitive safety prediction performance, highlighting that prediction correctness alone does not establish rationale reliability.

### Source excerpt

arXiv:2611.25793v1 Announce Type: new Abstract: Multimodal safety guards increasingly generate rationales alongside safety predictions, yet whether these rationales are reliable remains largely unexplored. We systematically study *rationale hallucination* from two perspectives: visual rationale hallucination, where rationales contain unsupported visual facts, and safety attribution hallucination, where grounded content is assigned an incorrect safety interpretation. Across rationale-generation methods, multiple vision-language backbones, and safety datasets, we find that rationale hallucination is widespread and does not consistently diminish with higher classification accuracy or increased model scale. Further analysis of the Think-with-Image paradigm shows that hallucination is concentrated in fine-grained attributes and relations, while visual tools are often invoked infrequently or without sufficient spatial focus. Based on these findings, we propose *Tool-Contrastive Grounding Reinforcement Learning* (TCG-RL), which rewards tool use only when it improves rationale grounding over a tool-free reference. TCG-RL substantially reduces rationale hallucination while maintaining competitive safety prediction performance. By revealing the gap between prediction correctness and rationale reliability, our study motivates a shift in multimodal safety guarding from outcome-only evaluation toward safety decisions that are both accurate and verifiably grounded.

## Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review

DevFeed: [Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review](<https://devfeed.tech/articles/survey-aware-machine-learning-a-guideline-for-valid-population-health-inference-based-on-scoping-review-144893.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.08963>)

Author: YongKyung Oh, Henry W. Zheng, Jeffrey Feng, Alex A. T. Bui

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>)

Tags: [cross-validation](<https://devfeed.tech/tags/cross-validation.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [design](<https://devfeed.tech/tags/design.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [health](<https://devfeed.tech/tags/health.md>), [inference](<https://devfeed.tech/tags/inference.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [ml](<https://devfeed.tech/tags/ml.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [models](<https://devfeed.tech/tags/models.md>), [nutrition](<https://devfeed.tech/tags/nutrition.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-evaluation](<https://devfeed.tech/tags/performance-evaluation.md>), [review](<https://devfeed.tech/tags/review.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [survey](<https://devfeed.tech/tags/survey.md>)

### AI overview

Standard ML evaluation on complex health surveys can produce biased estimates, understate uncertainty, and miss population-level disparities when it ignores sampling units, stratification, and weights. The paper proposes Survey-aware Machine Learning (SaML), a nine-step guideline for incorporating survey design metadata across the ML lifecycle. Its scoping review of 16 methodological papers summarizes weighted training, design-based cross-validation, and survey-adjusted performance evaluation, while identifying gaps in hyperparameter tuning and deployment. The guideline offers task-specific direction on which steps are needed for different analytical objectives.

### Source excerpt

arXiv:2605.08963v2 Announce Type: replace-cross Abstract: Machine Learning (ML) models trained on complex health surveys such as the National Health and Nutrition Examination Survey (NHANES) often ignore primary sampling units, stratification variables, and sampling weights. This practice violates the independence assumptions of standard evaluation methods. As a result, estimates become biased, uncertainty is underestimated, and fairness assessments fail to reflect population-level disparities. We propose Survey-aware Machine Learning (SaML), a nine-step guideline that incorporates survey design metadata across the ML lifecycle. Through a scoping review of 16 methodological papers, we summarize existing work on weighted model training, design-based cross-validation, and survey-adjusted performance evaluation. We also identify gaps in hyperparameter tuning and deployment. We provide task-specific guidance that clarifies which steps are required for different analytical objectives. SaML provides a checklist for valid population inference from survey data.

## Attention Head Specialization: Phase Transitions in Sample Complexity

DevFeed: [Attention Head Specialization: Phase Transitions in Sample Complexity](<https://devfeed.tech/articles/attention-head-specialization-phase-transitions-in-sample-complexity-145153.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26228>)

Author: L\\'eo Catteau, O. Duranthon, Lenka Zdeborov\\'a

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cascade](<https://devfeed.tech/tags/cascade.md>), [changes](<https://devfeed.tech/tags/changes.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [cond-mat-dis-nn](<https://devfeed.tech/tags/cond-mat-dis-nn.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [data-structure](<https://devfeed.tech/tags/data-structure.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [emergence](<https://devfeed.tech/tags/emergence.md>), [error](<https://devfeed.tech/tags/error.md>), [features](<https://devfeed.tech/tags/features.md>), [function](<https://devfeed.tech/tags/function.md>), [learning](<https://devfeed.tech/tags/learning.md>), [model](<https://devfeed.tech/tags/model.md>), [multi-head](<https://devfeed.tech/tags/multi-head.md>), [online](<https://devfeed.tech/tags/online.md>), [online-learning](<https://devfeed.tech/tags/online-learning.md>), [sample](<https://devfeed.tech/tags/sample.md>), [specialization](<https://devfeed.tech/tags/specialization.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The excerpt reports that BERT heads specialized to syntactic relations emerge as training dataset size increases. In a solvable high-dimensional multi-head attention model, specialization is a phase transition in sample complexity, marked by non-analytic changes in test error and other observables. Depending on data structure and regularization, heads may differentiate without conveying useful information, or specialize through successive transitions that recover progressively weaker latent features. The authors also relate these statistical transitions to stagewise specialization in online learning, separating statistical effects from training dynamics.

### Source excerpt

arXiv:2611.26228v1 Announce Type: new Abstract: Attention heads specialize into distinct functions during training, often emerging in stages together with sharp changes in model behavior. While this phenomenon has mostly been studied as a function of training time, we ask how head specialization depends on the amount of available training data. Empirically, we find that heads specialized to syntactic relations in BERT emerge as the dataset size increases. We then study this phenomenon in a solvable high-dimensional model of multi-head attention and establish that, in this model, head specialization is a genuine phase transition in sample complexity, corresponding to a non-analyticity in the test error and other observables. Depending on data structure and regularization, specialization can follow uninformative head differentiation or occur through a cascade of phase transitions that progressively recover weaker latent features, providing a statistical form of simplicity bias. Finally, we relate these statistical transitions to the stagewise emergence of specialized heads during online learning, disentangling statistical from dynamical origins of head specialization.

## BuggyMLE: Scaling Machine Learning Engineering Difficulty with Bug Injection

DevFeed: [BuggyMLE: Scaling Machine Learning Engineering Difficulty with Bug Injection](<https://devfeed.tech/articles/buggymle-scaling-machine-learning-engineering-difficulty-with-bug-injection-145007.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25088>)

Author: John Wu, Rushi Qiang, Yuchen Zhuang, Guowang Li, Girish Narayanswamy, Max Xu, Sam Schmidgall, Mark Malhotra, Shwetak Patel, Jimeng Sun, Daniel McDuff, Bo Dai, Xin Liu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bug](<https://devfeed.tech/tags/bug.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

BuggyMLE creates harder repository-level machine-learning engineering tasks by injecting controlled bugs into working ML repositories. Its Code Complexity Index uses ten structural features, including repository scale, dependency depth, and patch size; across eight coding benchmarks, it predicts average solve rates with R² = 0.951. From 222 repositories, the framework produces over 6,600 variants and nearly 260,000 lines of injected code. On BuggyMLE-Bench-Lite, the highest solve rate among 14 models falls from 95% at the easiest tier to 9% at the hardest. A three-level curriculum built from 200 additional repositories fine-tuned Qwen3.5-9B to rival frontier models on that benchmark; the model also improved reported results on SWE-bench Lite (24% to 33%) and LiveCodeBench v6 pass@1 (69% to 71%).

### Source excerpt

arXiv:2611.25088v1 Announce Type: cross Abstract: Enabling AI systems to autonomously improve AI models requires agents capable of performing machine learning engineering (MLE). In practice, designing, training, and evaluating complex models demands modifying multi-file repositories to reproduce results, debug training runs, integrate datasets, and port frameworks. However, existing MLE benchmarks limit agents to single-file edits without full repository or shell access, and common repository-level software engineering benchmarks have rapidly saturated. To address this, we introduce the Code Complexity Index (CCI), a difficulty metric based on ten structural features spanning repository scale, dependency depth, and patch size. CCI strongly predicts average solve rates across eight public coding benchmarks ($R^2 = 0.951$), identifying patch size and complexity as top predictors. Guided by CCI, we develop BuggyMLE, a scalable framework where agents inject controlled mutations into working ML repositories, synthesizing over 6,600 bug-injected MLE repository variants and nearly 260K lines of injected code based on 222 source repositories. Using BuggyMLE, we make two contributions. First, we construct BuggyMLE-Bench-Lite, the first difficulty-graded, repository-level variant of MLE-Bench Lite; across 14 evaluated models, the top solve rate drops from 95% to 9% as difficulty is scaled from the easiest to the hardest tier. Second, we synthesize a training curriculum across three difficulty levels over 200 additional ML repositories, fine-tuning a Qwen3.5-9B model to rival frontier models on BuggyMLE-Bench-Lite. Our trained model transfers beyond ML, raising its SWE-bench Lite resolve rate from 24% to 33% and its LiveCodeBench v6 pass@1 from 69% to 71%.

## Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models

DevFeed: [Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models](<https://devfeed.tech/articles/approximate-adjoint-models-for-memory-and-compute-efficient-online-learning-of-hybrid-models-145140.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26095>)

Author: Emilio Gonz\\'alez-Zamora, Pierre Tandeo, Laurent Debreu, Said Ouala

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [backpropagation](<https://devfeed.tech/tags/backpropagation.md>), [bptt](<https://devfeed.tech/tags/bptt.md>), [closure](<https://devfeed.tech/tags/closure.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [math-oc](<https://devfeed.tech/tags/math-oc.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [ocean](<https://devfeed.tech/tags/ocean.md>), [online](<https://devfeed.tech/tags/online.md>), [online-learning](<https://devfeed.tech/tags/online-learning.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>)

### AI overview

The proposed methods reduce the memory and compute costs of online hybrid-model training while preserving adjoint recurrence across the full trajectory. They compute exact pullbacks only at sparse anchor states; between anchors, Zero-order propagates sensitivities through the identity, while Pullback Reuse uses a frozen pullback. Reusing the pullback also lets the parameter-gradient sum factorize to one evaluation per chunk instead of one per time step. Across an incomplete Lorenz-63 model, a two-dimensional quasi-geostrophic turbulence closure, and bias correction in a multilayer quasi-geostrophic ocean model, peak memory fell by up to an order of magnitude and runtime by up to fourfold. Pullback Reuse stayed closest to the exact gradient direction, and both methods supported training at comparable accuracy. These are abstract-level reported results; no further experimental details are provided here.

### Source excerpt

arXiv:2611.26095v1 Announce Type: new Abstract: Differentiable programming enables online calibration of numerical models by minimizing errors accumulated along simulated trajectories. This includes estimating physical parameters and training neural sub-models in hybrid configurations. Gradients are typically computed using adjoint methods, or backpropagation through time (BPTT), whose computational and memory costs grow with the length of the training window. This limits the duration and resolution of hybrid-model training, a major bottleneck for realistic geophysical applications. Approaches like truncated BPTT reduces memory use by discarding sensitivities across truncation boundaries, introducing gradient bias and neglecting long-range dependencies. We propose a class of gradient approximation methods that preserve the adjoint recurrence over the full trajectory while approximating only the pullback operators within it. Exact pullbacks are computed by automatic differentiation at sparse anchor states only. Between anchors, sensitivities propagate either through the identity (Zero-order) or through a reused, frozen pullback (Pullback Reuse). This approximation makes the parameter pullback constant within each chunk, allowing the gradient sum to factorize so that a single evaluation per chunk replaces one per time step. We evaluate both on three systems of increasing complexity, an incomplete Lorenz-63 model, a large-eddy closure for two-dimensional quasi-geostrophic turbulence, and bias correction in a multilayer quasi-geostrophic ocean model. Peak memory falls by up to an order of magnitude and runtime up to fourfold, with Pullback Reuse staying closest to the exact gradient direction. In all three cases, approximate gradients support hybrid-model training at comparable accuracy, showing that effective online learning does not require exact gradients.

## Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data

DevFeed: [Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data](<https://devfeed.tech/articles/stop-removing-stopwords-how-an-inherited-preprocessing-default-distorts-legal-text-as-data-144926.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.19153>)

Author: Gregory M. Dickinson

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Data science and engineering](<https://devfeed.tech/topics/data-science-and-engineering.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [database](<https://devfeed.tech/tags/database.md>), [f1](<https://devfeed.tech/tags/f1.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [law](<https://devfeed.tech/tags/law.md>), [legal](<https://devfeed.tech/tags/legal.md>), [stop](<https://devfeed.tech/tags/stop.md>), [text](<https://devfeed.tech/tags/text.md>), [tf-idf](<https://devfeed.tech/tags/tf-idf.md>)

### AI overview

An exhaustive single-word ablation found no detectable benefit from stopword removal in two Supreme Court opinion classification tasks: ideological direction (7,668 opinions; baseline F1 about 0.68) and constitutional versus non-constitutional law type (7,001; about 0.92). The study tested roughly 18,500 words per task. Generic stoplists fell below the no-removal baseline in all twelve held-out tests; task-specific stoplists changed held-out F1 by only +0.0023 for ideology (95% CI −0.0124 to +0.0170) and +0.0001 for law type (−0.0082 to +0.0085). The authors argue that, in interpretable legal text-as-data pipelines, inherited preprocessing choices should be evaluated against the downstream objective because reshaping available features may alter the signal researchers aim to recover.

### Source excerpt

arXiv:2609.19153v3 Announce Type: replace-cross Abstract: Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study rather than a means to prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single word ablation that measures the effect of a preprocessing step directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~0.68) and constitutional versus non-constitutional law type (~0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of about 18,500 candidate words in turn, and a task-specific stoplist is built from the measurements. Common generic stoplists fall below the no-removal baseline in all twelve held-out tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and supplemental analysis finds that word-level statistics predict removal effects poorly, because true removal effects differ by less than the measurement can register, leaving little to predict. The method generalizes to any inherited preprocessing default; the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.

## Grid Cells as Spectral Successor Features: A Reusable Basis for Continual Reinforcement Learning

DevFeed: [Grid Cells as Spectral Successor Features: A Reusable Basis for Continual Reinforcement Learning](<https://devfeed.tech/articles/grid-cells-as-spectral-successor-features-a-reusable-basis-for-continual-reinforcement-learning-145188.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26504>)

Author: \\'Elodie C\\^ot\\'e-Gauthier, Doina Precup, Isabeau Pr\\'emont-Schwarz

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [basis](<https://devfeed.tech/tags/basis.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [eigenvectors](<https://devfeed.tech/tags/eigenvectors.md>), [features](<https://devfeed.tech/tags/features.md>), [grid](<https://devfeed.tech/tags/grid.md>), [linear-regression](<https://devfeed.tech/tags/linear-regression.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [policy](<https://devfeed.tech/tags/policy.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>)

### AI overview

The paper builds a reusable basis for continual reinforcement learning from eigenvectors of a fixed reference policy's transition matrix. In this basis, each successor feature is the corresponding base feature scaled by 1/(1−γλᵢ), so returns use the same features as immediate rewards; task adaptation becomes linear regression on reward, without a successor-feature network or replay buffer. The agent chooses actions greedily using the reference policy's action values, described as one step of policy improvement that suffices for a single goal. In a two-goal gridworld using a uniform-random-walk reference policy, the approach maintained near-maximal return through goal changes, while SimpleSF and DQN lost most of their return at each change. These results are limited to the described setting.

### Source excerpt

arXiv:2611.26504v1 Announce Type: new Abstract: Continual reinforcement learning requires agents to adapt when the task changes while reusing what they know about the environment. Successor features separate dynamics from task-specific reward, but their effectiveness depends on the choice of base features. Taking the identification of entorhinal grid cells with eigenvectors of the successor representation as a design principle, we build this basis from eigenvectors of the transition matrix of a fixed reference policy. With such a basis, the successor features at a state-action pair are a linear combination of the base features at that same pair, which is not true in general, and the coefficients are known in closed form: each successor feature is its base feature multiplied by $\theta_i = 1/(1-\gamma\lambda_i)$, where $\lambda_i$ is its eigenvalue. The long-term return is thus predicted from the same features as the immediate reward, no successor-feature network or replay buffer is needed, and adapting to a new task reduces to a linear regression on the reward. The agent acts greedily on the action values of the reference policy, which is one step of policy improvement over it and suffices to reach a single goal. In a two-goal gridworld, with the uniform random walk as reference policy, whose eigenvectors are the low-frequency Laplacian eigenvectors, agents built this way maintain near-maximal return across every change of goal, whereas SimpleSF and DQN lose most of their return at each change.

## Stability Bands for Feature Attribution: The Core, the Nucleolus and the Bargaining Set of Explained-Variance Games

DevFeed: [Stability Bands for Feature Attribution: The Core, the Nucleolus and the Bargaining Set of Explained-Variance Games](<https://devfeed.tech/articles/stability-bands-for-feature-attribution-the-core-the-nucleolus-and-the-bargaining-set-of-explained-variance-games-145027.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25238>)

Author: Fernando Delbianco, Fernando Tohm\\'e

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Plover](<https://devfeed.tech/topics/plover.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [band](<https://devfeed.tech/tags/band.md>), [battery](<https://devfeed.tech/tags/battery.md>), [boosting](<https://devfeed.tech/tags/boosting.md>), [certificate](<https://devfeed.tech/tags/certificate.md>), [coalition](<https://devfeed.tech/tags/coalition.md>), [contest](<https://devfeed.tech/tags/contest.md>), [convex](<https://devfeed.tech/tags/convex.md>), [core](<https://devfeed.tech/tags/core.md>), [cs-gt](<https://devfeed.tech/tags/cs-gt.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [econ-em](<https://devfeed.tech/tags/econ-em.md>), [economics](<https://devfeed.tech/tags/economics.md>), [feature](<https://devfeed.tech/tags/feature.md>), [features](<https://devfeed.tech/tags/features.md>), [game](<https://devfeed.tech/tags/game.md>), [games](<https://devfeed.tech/tags/games.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [gradient-boosting](<https://devfeed.tech/tags/gradient-boosting.md>), [graph](<https://devfeed.tech/tags/graph.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [variance](<https://devfeed.tech/tags/variance.md>)

### AI overview

The paper extends feature attribution beyond single Shapley values by reporting each feature's range of stable shares over the core, or the least core when the core is empty, with the nucleolus as a reference allocation. It defines coalition worth as the variance of predictions generated by a feature set. For linear models, the game is exactly 2-additive, with pairwise interactions driven by coefficient products and feature covariances; in any 2-additive game the prenucleolus equals the Shapley value, and core non-emptiness is characterized by non-negative interaction-graph cut weights. Convex games allow closed-form bands and minimum-cut certificates. In the reported examples, a coalition of Ratings, ROM, and Battery can object to a mean-SHAP allocation in a hedonic price model. A retail-orders gradient-boosting forecaster has an empty core and strong higher-order interactions; its nucleolus differs from Shapley by up to 0.19 variance shares, and sparse third-order surrogates recover it where pairwise surrogates do not.

### Source excerpt

arXiv:2611.25238v1 Announce Type: cross Abstract: Shapley-value attributions are the default way of explaining machine-learning predictions in economics, but they report a single number per feature and say nothing about whether a coalition of features that jointly accounts for more than it receives could contest that allocation. We study feature attribution through the core, the nucleolus and the bargaining set of an explained-variance game, in which the worth of a set of features is the variance of the model's predictions that those features generate. For every feature we report a stability band (its range of shares over the core, or over the least core when the core is empty), with the nucleolus as distinguished point and a certificate that the allocation admits no justified objection. Three results organise the approach. First, for linear models the game is exactly 2-additive, with pairwise Harsanyi dividends $2\beta_i\beta_j\sigma_{ij}$, so multicollinearity is what creates coalitional structure. Second, in every 2-additive game the prenucleolus coincides with the Shapley value, the (least) core is point-symmetric around it, and the core is non-empty if and only if every cut of the interaction graph has non-negative weight. The Shapley value thus always lies in the prebargaining set, and stability adds information only through band widths and interactions of order three or more. Third, for convex games the bands have a closed form and any allocation can be certified with one minimum cut. In a hedonic price model, the usual mean-SHAP explanation admits a justified objection by the coalition {Ratings, ROM, Battery}. In a gradient-boosting forecaster of retail orders the exact game has an empty core and strong higher-order interactions; the nucleolus departs from the Shapley value by up to 0.19 variance shares, and sparse third-order surrogates recover it where pairwise ones cannot.

## On the Impact of Feature Reduction Techniques on Adversarial Attacks

DevFeed: [On the Impact of Feature Reduction Techniques on Adversarial Attacks](<https://devfeed.tech/articles/on-the-impact-of-feature-reduction-techniques-on-adversarial-attacks-145002.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25004>)

Author: Mohammad Meymani, Roozbeh Razavi-Far

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [adversarial-machine-learning](<https://devfeed.tech/tags/adversarial-machine-learning.md>), [apt](<https://devfeed.tech/tags/apt.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [defense](<https://devfeed.tech/tags/defense.md>), [effect](<https://devfeed.tech/tags/effect.md>), [f1](<https://devfeed.tech/tags/f1.md>), [feature](<https://devfeed.tech/tags/feature.md>), [features](<https://devfeed.tech/tags/features.md>), [impact](<https://devfeed.tech/tags/impact.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [information](<https://devfeed.tech/tags/information.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [machine-learning-models](<https://devfeed.tech/tags/machine-learning-models.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [techniques](<https://devfeed.tech/tags/techniques.md>)

### AI overview

On the APT dataset, permutation importance ranking and univariate mutual information generally yielded the most consistent robustness improvements across the evaluated classifiers and attacks. The study compares PCA, permutation importance ranking, recursive feature elimination, and univariate mutual information across SVM, decision tree, random forest, MLP, and k-nearest neighbors models, under poisoning, backdoor, and universal adversarial perturbation attacks. It evaluates accuracy, F1-score, and mitigation score; the abstract says results for the other reduction methods vary by classifier and attack scenario.

### Source excerpt

arXiv:2611.25004v1 Announce Type: new Abstract: Adversarial attacks have posed significant threats to machine learning models by exploiting their inherent vulnerabilities. Researchers have established an interdisciplinary field called adversarial machine learning to explore these vulnerabilities and develop corresponding defense strategies. Feature reduction strategies are used to decrease the dimensionality of the data in order to reduce training time, avoid the curse of dimensionality, prevent overfitting, and mitigate redundant features. However, their effect on adversarial robustness across different classifiers and attack scenarios remains insufficiently explored. This study aims to analyze the effect of feature reduction techniques on the adversarial robustness of a diverse set of machine learning models under poisoning, backdoor, and universal adversarial perturbation attacks on the APT dataset. These models include support vector machine, decision tree, random forest, multi-layer perceptron, and k-nearest neighbors. The attained results are compared with scenarios where different feature reduction techniques are applied, including principal component analysis, permutation importance ranking, recursive feature elimination, and univariate mutual information. Metrics such as accuracy, F1-score, and mitigation score are employed to evaluate the effect of these techniques on adversarial robustness. The results demonstrate that permutation importance ranking and univariate mutual information generally provide the most consistent robustness improvements, while other methods exhibit more variable effects depending on the classifier and attack scenario.

## DL101 The Representation Capability of Neural Network Models

DevFeed: [DL101 The Representation Capability of Neural Network Models](<https://devfeed.tech/articles/dl101-the-representation-capability-of-neural-network-models-144995.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24980>)

Author: Fernando Berzal

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [deep](<https://devfeed.tech/tags/deep.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [error](<https://devfeed.tech/tags/error.md>), [gradient-descent](<https://devfeed.tech/tags/gradient-descent.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [regions](<https://devfeed.tech/tags/regions.md>), [relu](<https://devfeed.tech/tags/relu.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [tangent](<https://devfeed.tech/tags/tangent.md>), [training](<https://devfeed.tech/tags/training.md>), [universal-approximation](<https://devfeed.tech/tags/universal-approximation.md>), [universality](<https://devfeed.tech/tags/universality.md>)

### AI overview

Universal approximation shows that shallow neural networks with non-polynomial activations can approximate any continuous function on compact sets, but it gives no guarantees about model size, successful training, or generalization. Barron's results provide quantitative approximation rates for functions with bounded Fourier norm. Montúfar's result shows that deep networks can form exponentially more linear regions as depth increases; the excerpt states that, for the same parameter count, they are more expressive than shallow networks. These results explain representational capacity, not whether training will achieve it.

### Source excerpt

arXiv:2611.24980v1 Announce Type: cross Abstract: Universal approximation theorems (Cybenko, Funahashi, Hornik & Leshno) provide the mathematical justification for why neural networks are powerful enough to model complex, nonlinear phenomena. Shallow networks can approximate any continuous function on compact sets. Leshno's theorem clarified that non-polynomial activations are necessary for universality, which explains why ReLU, logistic, hyperbolic tangent, and other common activations work (but pure polynomials do not). However, approximation theorems provide no efficiency, training, nor generalization guarantees. They do not indicate how many neurons are needed for a given accuracy, whether gradient descent will find the right parameters, or whether networks trained on finite data will generalize well. Barron provided quantitative error bounds for particular function classes (approximation rates for functions with bounded Fourier norm), whereas Mont\'ufar was the first to show that expressivity grows exponentially with depth (in terms of the number of linear regions). Deep networks are strictly more expressive than shallow ones with the same number of parameters. Depth is fundamentally more powerful than width, providing a rigorous mathematical explanation for the use of deep learning models.

## How Network Topology and Data Heterogeneity Shape Decentralized Learning: A Spectral Analysis

DevFeed: [How Network Topology and Data Heterogeneity Shape Decentralized Learning: A Spectral Analysis](<https://devfeed.tech/articles/how-network-topology-and-data-heterogeneity-shape-decentralized-learning-a-spectral-analysis-145143.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26104>)

Author: Luigi Palmieri, Lorenzo Valerio, Chiara Boldrini, Andrea Passarella, Marco Conti, J\\'anos Kert\\'esz

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [communication](<https://devfeed.tech/tags/communication.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [influence](<https://devfeed.tech/tags/influence.md>), [information](<https://devfeed.tech/tags/information.md>), [irregular](<https://devfeed.tech/tags/irregular.md>), [learning](<https://devfeed.tech/tags/learning.md>), [network](<https://devfeed.tech/tags/network.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

The paper separates decentralized learning's topology effects into two mechanisms: the dominant eigenmode sets the consensus trajectory and node influence, while non-dominant eigenmodes govern disagreement. Under uniform neighborhood averaging, stationary influence is proportional to node degree plus one; the authors also derive a disagreement bound involving spectral mixing and gradient heterogeneity. Experiments report nearly identical learning dynamics across regular and heterogeneous topologies with IID data. With non-IID data, network size and connectivity affect how unevenly information is learned, and the distribution of data across nodes shapes local contributions to consensus.

### Source excerpt

arXiv:2611.26104v1 Announce Type: new Abstract: Network topology influences decentralized federated learning through information mixing and the relative contribution of individual nodes. While existing analyses primarily focus on spectral mixing properties, they often assume doubly stochastic aggregation, overlooking topology-dependent influence under irregular communication networks. We develop a spectral framework that separates two complementary mechanisms: the dominant eigenmode determines the consensus trajectory and node influence, while non-dominant eigenmodes govern the propagation and attenuation of disagreement. Under uniform neighborhood averaging, we show that the stationary influence is proportional to node degree plus one and derive a bound relating model disagreement to spectral mixing and gradient heterogeneity. We then investigate how these mechanisms interact with the data distribution across nodes. Experiments across regular and heterogeneous network topologies reveal nearly identical learning dynamics under IID data, while network size and connectivity affect how unevenly distributed information is learned under non-IID data. For non-IID settings, we characterize how the distribution of data across nodes shapes the relative contribution of local information to consensus dynamics.

## STARK: Moving towards Personalized Agents That Truly Learn and Remember

DevFeed: [STARK: Moving towards Personalized Agents That Truly Learn and Remember](<https://devfeed.tech/articles/stark-moving-towards-personalized-agents-that-truly-learn-and-remember-145574.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25705>)

Author: Aryan Jain, Abhishek Jha, Anish Nediyanchath, Promod Yenigalla

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [cold-start](<https://devfeed.tech/tags/cold-start.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory-architecture](<https://devfeed.tech/tags/memory-architecture.md>), [rouge](<https://devfeed.tech/tags/rouge.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>)

### AI overview

STARK uses two linked graphs to store long-term user memory: an Episodic Graph of temporally, causally, and semantically connected interactions, and an Insight Graph of behavioral signals supported by those events. At inference, it retrieves grounded insights directly instead of repeatedly traversing episodes. Representing events as links between insights also supports relational embeddings for transferring knowledge across users in shared contexts and inferring missing insights for cold-start users. The abstract reports gains over state of the art of 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open-domain questions. On LongLaMP, cross-user transfer at 5% graph sparsity improves open-ended judge scores by 0.7 points and ROUGE-L by 3.

### Source excerpt

arXiv:2611.25705v1 Announce Type: cross Abstract: Long-term memory is essential for personalized agentic systems that interact with users over long time periods, yet current architectures only capture what happened while leaving the reasoning of why it happened to be derived later by underlying LLMs.%, and silo knowledge within individual users. These events can, however, convey not only what a user experienced but also how that experience shaped their behavioral patterns. We introduce STARK, a dual-graph memory architecture which treats these events not just as nodes but also as edges between behavioral insights. STARK maintains an Episodic Graph which records interactions as temporally, causally, and semantically linked episodes; and an Insight Graph which represents LLM-extracted behavioral signals scored by how many events support them, connected by the very events that led to them. At inference, behavioral knowledge is retrieved directly from insight nodes grounded by event-as-edges, eliminating repeated episodic traversal. The event-as-edge structure also naturally enables projecting the knowledge graph into a relational embedding space where cross-user transfer becomes possible under shared contextual circumstances, allowing the system to infer missing insights for cold-start users. Evaluations show that STARK improves by 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open domain questions over state of the art. On the public LongLaMP abstract-generation benchmark, cross-user transfer improves open-ended judge scores by 0.7 points and ROUGE-L by 3 at 5% graph sparsity.

## RePAIR: Predictive Self-Supervised Representation Learning in Chess

DevFeed: [RePAIR: Predictive Self-Supervised Representation Learning in Chess](<https://devfeed.tech/articles/repair-predictive-self-supervised-representation-learning-in-chess-144905.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.11860>)

Author: Christoph Koller, Johannes F\\"urnkranz, Timo Bertram

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Self-supervised learning](<https://devfeed.tech/topics/self-supervised-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [bert](<https://devfeed.tech/topics/bert.md>)

Tags: [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [bert](<https://devfeed.tech/tags/bert.md>), [chess](<https://devfeed.tech/tags/chess.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [space](<https://devfeed.tech/tags/space.md>)

### AI overview

RePAIR learns compact representations of consecutive chess positions by masking large portions of latent-state sequences, then using a lightweight predictor to repair the gaps in a lower-dimensional embedding space. The authors report that its encoder clusters meaningful chess concepts, and that reconstructing masked board states captures piece movements without reinforcement learning. They also use trajectories through the representation space to inspect games. These findings are reported for chess; the supplied excerpt does not establish performance on other sequential data.

### Source excerpt

arXiv:2606.11860v2 Announce Type: replace Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MAE. Then, we apply a lightweight Predictor to the latent representations that repairs gaps in the sequence in a lower-dimensional embedding space akin to JEPA. Our experiments in the domain of chess show that the Encoder refines the board representations such that meaningful chess concepts emerge clustered in the latent space. Furthermore, reconstructions of the masked board states show that the model is able to reason about the piece movements without relying on costly reinforcement learning methods. Lastly, we find that the resulting representation space allows for quick and intuitive dissections of chess games by observing the game path trajectories in this semantically rich space.

## When Do Rankings Beat Signs? Gradient Direction Recovery under Even Nuisance

DevFeed: [When Do Rankings Beat Signs? Gradient Direction Recovery under Even Nuisance](<https://devfeed.tech/articles/when-do-rankings-beat-signs-gradient-direction-recovery-under-even-nuisance-145132.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26055>)

Author: Zhuangzhuang Pan, Yan Xia, Chee Seng Chan

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [angular](<https://devfeed.tech/tags/angular.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [batch](<https://devfeed.tech/tags/batch.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cycles](<https://devfeed.tech/tags/cycles.md>), [dimensions](<https://devfeed.tech/tags/dimensions.md>), [error](<https://devfeed.tech/tags/error.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [full](<https://devfeed.tech/tags/full.md>), [function](<https://devfeed.tech/tags/function.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [hierarchy](<https://devfeed.tech/tags/hierarchy.md>), [information](<https://devfeed.tech/tags/information.md>), [rankings](<https://devfeed.tech/tags/rankings.md>), [recovery](<https://devfeed.tech/tags/recovery.md>)

### AI overview

For fixed-center gradient direction recovery with a linear signal and an unknown differentiable even nuisance, coupling reversed cross-pair rankings can reduce one-round evaluation cost when relative shell variation is at most cε/√d. Reverse reaches angular accuracy ε with Õ(d + √(d/ε)) evaluations, matching a lower bound up to logarithmic factors, versus Θ(d/ε) for within-pair signs alone on the same class; the decoder need not be given the variation bound. For well-conditioned positive-definite quadratics without a shared relative-curvature bound, the R-round minimax cost is Θ(dR(ε^(-1/R) − 1)) even with cumulative rankings. The abstract also reports validity beyond exact evenness given error bounds and lower terminal mean gaps for short-cycle recovery on two ridge tasks against tested batch-capable controls under joint caps. It does not establish an added optimization benefit from fitting the full ranking.

### Source excerpt

arXiv:2611.26055v1 Announce Type: new Abstract: Can ranking a batch of antipodal query pairs recover a gradient direction with fewer evaluations than using within-pair signs alone? We study fixed-center recovery in $d$ dimensions for a linear signal plus an unknown differentiable even nuisance, counting function evaluations and feedback rounds separately. Shared pair offsets create an information hierarchy: Mirror retains within-pair signs, Reverse couples reversed cross-pair orders to cancel offsets, and Full enforces all ranking inequalities. Relative shell variation is the nuisance range over the query sphere normalized by the linear-signal scale. When it is at most $c\varepsilon/\sqrt{d}$, Reverse localizes every consistent direction to angular accuracy $\varepsilon$ using $\widetilde{O}(d+\sqrt{d/\varepsilon})$ evaluations in one round at fixed confidence, without a variation bound supplied to the decoder. This matches a lower bound up to logarithmic factors, versus the $\Theta(d/\varepsilon)$ one-round sign-only minimax cost on the same class. Over well-conditioned positive-definite quadratics with no common relative-curvature bound, the $R$-round minimax cost is instead $\Theta(dR(\varepsilon^{-1/R}-1))$, even with cumulative rankings. We extend validity beyond exact evenness under supplied error bounds. Matched-endpoint experiments certify information beyond signs and short cycles. On two ridge tasks under joint evaluation and round caps, short-cycle recovery attains lower terminal mean gaps than the tested batch-capable controls. An additional optimization benefit from fitting the complete ranking remains unestablished.

## The Stability Gap in Continual Reinforcement Learning

DevFeed: [The Stability Gap in Continual Reinforcement Learning](<https://devfeed.tech/articles/the-stability-gap-in-continual-reinforcement-learning-145157.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26252>)

Author: Sebastian Pusch, Matthia Sabatelli, Gido M. van de Ven

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [crl](<https://devfeed.tech/tags/crl.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [inexpensive](<https://devfeed.tech/tags/inexpensive.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [performance](<https://devfeed.tech/tags/performance.md>), [proof-of-concept](<https://devfeed.tech/tags/proof-of-concept.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

The work introduces a simple continual reinforcement learning benchmark that varies observation representations while keeping environment dynamics and rewards fixed. It uses the benchmark to show a stability gap: after new tasks are introduced, performance on prior tasks drops substantially, then partially or fully recovers, even though the agent retains complete access to those past tasks. The authors say the benchmark supports proof-of-concept demonstrations, inexpensive experiments, and reproducible sanity checks; the excerpt does not specify particular agents or benchmark results beyond this finding.

### Source excerpt

arXiv:2611.26252v1 Announce Type: new Abstract: Continual reinforcement learning (CRL) aims to enable agents to adapt to changing tasks while preserving previously acquired capabilities. Evaluation often relies on final aggregate metrics that can hide temporary performance degradation during adaptation. This work introduces a simple CRL benchmark that varies observation representations while preserving environment dynamics and rewards, supporting proof-of-concept demonstrations, inexpensive experimentation, and easily reproducible sanity checks. Using this benchmark, we demonstrate the stability gap in CRL: a substantial drop in prior-task performance after the introduction of new tasks, followed by partial or complete recovery. This pattern occurs despite the agent having complete access to past tasks.

## Should Belgians Install an Advanced Energy Management System in Their Electrified Dwelling ?

DevFeed: [Should Belgians Install an Advanced Energy Management System in Their Electrified Dwelling ?](<https://devfeed.tech/articles/should-belgians-install-an-advanced-energy-management-system-in-their-electrified-dwelling-145182.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26441>)

Author: Julian Ruddick, Cedric De Cauwer, Thierry Coosemans, Maarten Messagie

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [belgium](<https://devfeed.tech/tags/belgium.md>), [benefits](<https://devfeed.tech/tags/benefits.md>), [completion](<https://devfeed.tech/tags/completion.md>), [control](<https://devfeed.tech/tags/control.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [decision-trees](<https://devfeed.tech/tags/decision-trees.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [electric](<https://devfeed.tech/tags/electric.md>), [electric-vehicles](<https://devfeed.tech/tags/electric-vehicles.md>), [energy](<https://devfeed.tech/tags/energy.md>), [heat-pumps](<https://devfeed.tech/tags/heat-pumps.md>), [learning](<https://devfeed.tech/tags/learning.md>), [load](<https://devfeed.tech/tags/load.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mpc](<https://devfeed.tech/tags/mpc.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prices](<https://devfeed.tech/tags/prices.md>)

### AI overview

A simulation of 500 representative Belgian dwellings under a 2023 contract with hourly prices and a monthly peak tariff found modest savings from advanced energy management. Against a rule-based controller, annual average savings were EUR 82.50 for TreeC, EUR 116.60 for model predictive control (MPC), and EUR 177.40 for MPC with perfect forecasts, used as an upper bound. Thermal comfort was similar across systems (26-31 Kh). MPC saved more, while TreeC achieved higher EV charge completion (93.3% versus 88.8% for MPC, with a 95% maximum) and a smoother aggregate load. Estimated purchase costs (EUR 280-680) and subscriptions (EUR 0-360 per year) make the savings unattractive for widespread adoption. The findings reflect the simulated dwellings and stated pricing conditions.

### Source excerpt

arXiv:2611.26441v1 Announce Type: cross Abstract: As dwellings electrify and more complex electricity pricing spreads in Belgium, the question arises: What are the potential benefits of installing an advanced energy management systems in an electrified Belgian dwelling ? To answer this question, we simulate 500 representative Belgian dwellings in which fossil systems are replaced by controllable electric technologies: space heating via air-to-air heat pumps, domestic hot water via electric boilers, and private transport via electric vehicles with home chargers. Photovoltaic systems are assigned according to current adoption rates. We evaluate two advanced energy management systems (EMS): model predictive control (MPC) and TreeC, a machine learning method using decision trees to model the EMS strategy. These are compared to a rule-based controller (RBC) that mimics default operation and an MPC with perfect forecasts (MPC P) as an upper bound. Performance for these EMSs is assessed for 2023 under a real contract with hourly prices and a monthly peak tariff. Average annual savings versus RBC are 82.5 EUR, 116.6 EUR, and 177.4 EUR for TreeC, MPC, and MPC P, respectively. All EMSs deliver similar thermal comfort (26-31 Kh). MPC saves more, while TreeC achieves higher EV charge completion (93.3% vs 88.8% for MPC, with a max charge of 95%) and a smoother aggregate load across the 500 dwellings. Savings remain modest relative to EMS purchase (280-680 EUR) and subscription (0-360 EUR/year) costs which is not favourable towards widespread adoption. The data and code to reproduce this study are available at https://github.com/EVERGi/should_belgians_install_advanced_ems_paper.

## Fixing the Twin, Not the Detector: Sim-to-Real Roadside LiDAR Detection from Digital-Twin Data

DevFeed: [Fixing the Twin, Not the Detector: Sim-to-Real Roadside LiDAR Detection from Digital-Twin Data](<https://devfeed.tech/articles/fixing-the-twin-not-the-detector-sim-to-real-roadside-lidar-detection-from-digital-twin-data-145130.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26035>)

Author: KuanLin Chen, Feng-jui Kuo

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [lidar](<https://devfeed.tech/tags/lidar.md>), [model](<https://devfeed.tech/tags/model.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [point](<https://devfeed.tech/tags/point.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [sim](<https://devfeed.tech/tags/sim.md>), [sim-to-real](<https://devfeed.tech/tags/sim-to-real.md>), [site](<https://devfeed.tech/tags/site.md>), [size](<https://devfeed.tech/tags/size.md>), [static](<https://devfeed.tech/tags/static.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [synthetic-data](<https://devfeed.tech/tags/synthetic-data.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

A synthetic-only CenterPoint pipeline achieved first place in the UrbanTwin challenge's LUMPI track (0.5541 combined score) and fifth in V2X-Real (0.8102), with most gains attributed to correcting twin-to-site differences. The approach aligns coordinates, point density, and box conventions; adds pedestrians, riders, and unlabeled street clutter; and rebuilds twin objects at real-world size and density. Non-learned resampling raised LUMPI realism from 0.589 to 0.947, close to the 0.949 similarity between real frames. Label-free post-processing uses recurring static structures and real-object point statistics. Systematic corrections generally retained one-quarter to three-quarters of validation gains on test data, while choices fitted to the few validation objects did not transfer. Detectors were trained only on synthetic data using a single 8 GB laptop GPU.

### Source excerpt

arXiv:2611.26035v1 Announce Type: cross Abstract: Roadside LiDAR detectors are expensive to train on real labels, and digital twins promise to replace these labels, but a detector trained on a twin meets a different sensor, different objects and different annotation conventions on the real site. We describe the pipeline that placed first in the LUMPI track of the UrbanTwin Sim2Real LiDAR Challenge (IEEE BigData 2026 Cup, 0.5541 combined score) and fifth on its V2X-Real track (0.8102). Every detector is a CenterPoint model trained only on synthetic data, on a single 8 GB laptop GPU. Most of the gain came from correcting differences between the twin and the real site rather than from the detector. We align the twin's coordinates, point density and box convention with the test sensor, generate the pedestrians and riders that the twins lack, plus street clutter as unlabeled negatives, and rebuild twin objects at real size and real point density. A non-learned resampling to the per-cell point density of unlabeled real frames lifts LUMPI realism from 0.589 to 0.947, against 0.949 between real frames. Label-free post-processing then exploits what a fixed roadside sensor guarantees: static structures recur in every frame, and real objects have characteristic point statistics. Reporting the validation and test gain of each component side by side, we find that corrections of systematic sim-to-real differences transfer to the test set, typically keeping a quarter to three quarters of their validation gain, while choices that fit the few objects of a validation set do not.

## Learning to Verify: Signature-Guided Training for Adaptive Adversarial Detection

DevFeed: [Learning to Verify: Signature-Guided Training for Adaptive Adversarial Detection](<https://devfeed.tech/articles/learning-to-verify-signature-guided-training-for-adaptive-adversarial-detection-145031.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25271>)

Author: Arash Vashagh, Roozbeh Razavi-Far

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [learning](<https://devfeed.tech/tags/learning.md>), [training](<https://devfeed.tech/tags/training.md>), [verify](<https://devfeed.tech/tags/verify.md>)

### AI overview

The approach keeps the classifier fixed and trains a separate verifier to assess its predictions. During training, class-specific activation signatures guide the creation of difficult adversarial examples; knowledge distillation helps the verifier retain performance on clean inputs. At inference, it checks predictions without using the signatures. On the evaluated datasets, it substantially outperformed confidence-based and feature-based detectors against the tested adaptive L-infinity attacks, including attacks unseen in training. Ablations attribute most of the robustness gain to adaptive verifier training, while signature guidance mainly helps clean accuracy. Additional L2 evaluations expose limits to robustness across perturbation types.

### Source excerpt

arXiv:2611.25271v1 Announce Type: new Abstract: Adversarial example detectors often fail when attackers explicitly attempt to bypass them. We propose a dual-model approach that keeps the original classifier fixed and trains a separate verifier to assess its predictions. During training, we identify patterns of internal neural network activations that distinguish genuine examples of each class from adversarial examples targeting that class. These patterns, called activation signatures, guide the generation of challenging adversarial examples that mislead the classifier, challenge the verifier, and internally resemble the target class. The verifier learns to recognize these examples while preserving its performance on clean inputs through knowledge distillation. At inference, the verifier evaluates the classifier's prediction without requiring activation signatures. We evaluate the approach on publicly available datasets against several adaptive attacks, including attacks unseen during training. The proposed verifier substantially outperforms directly attacked confidence-based and feature-based detectors under the evaluated L-infinity attacks. Ablation studies show that adaptive verifier training is the main source of this improvement, while signature guidance primarily benefits clean accuracy. Additional L2 evaluations reveal limitations in robustness across perturbation types.

## Optimizer-dependent training dynamics converge to the same one-third optimal data scaling

DevFeed: [Optimizer-dependent training dynamics converge to the same one-third optimal data scaling](<https://devfeed.tech/articles/optimizer-dependent-training-dynamics-converge-to-the-same-one-third-optimal-data-scaling-144944.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.37745>)

Author: Hyunseok Lee, Mihir Basil, Yizhou Liu, Jeff Gore

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [scaling laws](<https://devfeed.tech/topics/scaling-laws.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

In an online teacher-student model, the training-step loss decay depends on the optimizer, while the optimally tuned loss scales as dataset size D to the −1/3 across the seven optimizers studied. The authors split loss into radial norm growth and tangential alignment. For SGD, both decay exponents are near 1/3; for Adam, they differ substantially (about 0.48 and 0.08). This difference makes the optimal learning rate independent of D for SGD but decreasing with D for Adam. A stochastic-dynamics analysis relates the channels through 2αr + αt = 1, yielding the shared optimal data exponent. The abstract reports that optimizers change the prefactor and per-step learning dynamics, but not the tuned loss rate per sample.

### Source excerpt

arXiv:2609.37745v2 Announce Type: replace Abstract: Neural scaling, in which loss falls as a power law with training, is central to large language models, and one recent proposal is that a $1/3$ exponent emerges from learning peaked distributions. That account describes SGD, but models in practice are trained with adaptive optimizers. Here we separate two exponents the $1/3$ account does not distinguish: how fast the loss falls with training steps along a single run, and how fast the optimally tuned loss falls with dataset size $D$. We show that the first, a dynamic exponent, is optimizer-specific while the second, an optimal data exponent, converges to $1/3$ across optimizers. In an online teacher-student model we decompose the loss into norm growth (radial) and alignment toward the teacher direction (tangential), each decaying as a power law with dynamic exponents $\alpha_{r}$ and $\alpha_{t}$. Under SGD, both are close to $1/3$, so the data exponent is also $1/3$ across different learning rates. Under Adam the two separate: $\alpha_{r} \simeq 0.48$ but $\alpha_{t} \simeq 0.08$. Since the total loss is minimized when these two parts are balanced, the optimal learning rate is optimizer-dependent: $D$-independent for SGD but falls with $D$ for Adam. Yet tuned to that optimum, the loss returns to $D^{-1/3}$ for both. A stochastic-dynamics analysis explains why: the optimizers can trade decay speed between the two channels, but they all fall on a single dynamic exponent relation, $2\alpha_{r}+ \alpha_{t} = 1$, which fixes the optimal data exponent at $1/3$. Across seven optimizers, including Muon, the measured exponents are consistent with this relation, and the optimal-loss envelopes agree with $D^{-1/3}$ across them. The optimizer sets how fast a model learns per step; tuned optimally, it changes the prefactor but not the rate at which loss falls per sample.

## Safeguarded Learning-Assisted Nonlinear Conjugate Gradient Methods

DevFeed: [Safeguarded Learning-Assisted Nonlinear Conjugate Gradient Methods](<https://devfeed.tech/articles/safeguarded-learning-assisted-nonlinear-conjugate-gradient-methods-145093.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25707>)

Author: Morteza Kimiaei, Saman Babaie--Kafaki

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [example](<https://devfeed.tech/tags/example.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [learning](<https://devfeed.tech/tags/learning.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [machine](<https://devfeed.tech/tags/machine.md>), [math-oc](<https://devfeed.tech/tags/math-oc.md>), [online-learning](<https://devfeed.tech/tags/online-learning.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [problems](<https://devfeed.tech/tags/problems.md>), [reduce](<https://devfeed.tech/tags/reduce.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [storage](<https://devfeed.tech/tags/storage.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

The framework adds two online extreme learning machine models to classical nonlinear conjugate gradient methods while retaining their standard two-term structure. One predicts a coefficient during restart recovery or persistent stagnation; the other proposes a bounded correction to the fallback step size after a finite-precision line-search failure. Predictions are accepted only if they meet descent, scale, and out-of-distribution safeguards; otherwise deterministic recovery remains in place. The models train on trajectory data without extra function or gradient evaluations. Across six variants tested on 480 CUTEst problems, the abstract reports improved robustness at broadly comparable evaluation costs. A conductivity-identification example also suggests potential savings in evaluations and computation time when evaluations are expensive.

### Source excerpt

arXiv:2611.25707v1 Announce Type: cross Abstract: A learning-assisted framework for Nonlinear Conjugate Gradient (NCG) methods is developed in which lightweight online prediction is used to support, rather than replace, the classical optimization process. The proposed approach retains the standard two-term NCG structure and introduces two independent online extreme learning machine models. The first model predicts an NCG coefficient during restart recovery or when persistent stagnation is detected, whereas the second model is used only after a line-search failure in finite precision arithmetic to propose a bounded correction to the deterministic fallback step size. Neural predictions are accepted only when they satisfy deterministic numerical safeguards, including descent, scale, and out-of-distribution requirements; otherwise, the corresponding deterministic recovery or fallback mechanism is retained. Both learning models are updated online using quantities already generated along the optimization trajectory and therefore require no additional function or gradient evaluations for training. These learning frameworks are applied to six well-known classical NCG methods, producing corresponding low-storage learning-assisted variants with deterministic safeguards. Numerical experiments on 480 CUTEst test problems show improved robustness for all six variants at broadly comparable evaluation costs. A PDE-constrained conductivity-identification example further illustrates the potential of the proposed approach to reduce evaluation costs and computational time for problems with expensive function and gradient evaluations. These findings suggest that restricted online learning can improve the robustness and computational performance of classical NCG methods while preserving their low-storage structure and deterministic optimization safeguards, and is particularly promising when function or gradient evaluations are expensive.

## Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees

DevFeed: [Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees](<https://devfeed.tech/articles/measurement-budget-allocation-in-quantum-learning-with-finite-shot-generalization-guarantees-145364.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.24891>)

Author: Ferhat Ozgur Catak

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [quantum mechanics](<https://devfeed.tech/topics/quantum-mechanics.md>), [Error Propagation](<https://devfeed.tech/topics/error-propagation.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [budget](<https://devfeed.tech/tags/budget.md>), [circuit](<https://devfeed.tech/tags/circuit.md>), [circuits](<https://devfeed.tech/tags/circuits.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [learning](<https://devfeed.tech/tags/learning.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [noise](<https://devfeed.tech/tags/noise.md>), [plan](<https://devfeed.tech/tags/plan.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [qubit](<https://devfeed.tech/tags/qubit.md>), [sample](<https://devfeed.tech/tags/sample.md>), [score](<https://devfeed.tech/tags/score.md>), [simulations](<https://devfeed.tech/tags/simulations.md>), [study](<https://devfeed.tech/tags/study.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

With a fixed measurement budget, the paper balances the number of training states against shots per state for binary quantum classifiers. Its distribution-free bound has a sample term of order √(d/n) and a shot term of order √(log n/S); under B=nS these trade off. Minimizing a closed-form surrogate yields n*=2√(2dB/log(4B/δ)) and S*=B/n*, with a worst-case rate of B⁻¹⁄⁴. In PennyLane simulations across nine synthetic benchmarks, the empirical gap remained below the bound, but the bound was vacuous at simulated budgets and became non-vacuous only at larger budgets (about B>=5000 for d=4). With concave loss, the gap was U-shaped and the shot contribution matched the analysis; with absolute loss, shot noise was unbiased and no shot-limited regime appeared. The rule is proposed for planning finite-shot evaluations.

### Source excerpt

arXiv:2608.24891v2 Announce Type: replace Abstract: On near-term quantum hardware, estimating a Born probability requires repeated circuit executions. A quantum learning experiment with a fixed measurement budget $B$ must therefore decide how many distinct training states $n$ to use and how many shots $S$ to spend on each. We study this trade-off for binary quantum classifiers whose measurement operator $M$ is learned from the training data and evaluated with fresh measurement outcomes. We prove a distribution-free generalization bound for bounded, $L$-Lipschitz losses with a sample term of order $\sqrt{d/n}$ and a shot term of order $\sqrt{(\log n)/S}$; under $B=nS$ the two terms move in opposite directions. Minimizing a closed-form surrogate of the bound gives the allocation rule $n^* = 2\sqrt{2dB/\log(4B/\delta)}$, $S^* = B/n^*$, whose bound value is within 0.1% of the exact numerical minimum on all budgets we evaluate, and a worst-case rate of $B^{-1/4}$. PennyLane simulations with 2- and 4-qubit variational circuits on nine synthetic benchmarks show that the empirical gap stays below the bound in all configurations, although the bound is vacuous at the simulated budgets and becomes non-vacuous only for larger budgets (e.g., $B \gtrsim 5000$ for $d=4$). For a loss that is concave in the score, the empirical gap is U-shaped under a fixed budget and the measured shot contribution matches its analytical value; for the absolute loss, shot noise is unbiased and no shot-limited regime appears. The rule can be used to plan finite-shot evaluations before an experiment is run.

[Next page](<https://devfeed.tech/topics/machine-learning.md?cursor=WyIyMDI2LTExLTIwVDA1OjAwOjAwKzAwOjAwIiwgImJiOTI2ZmRiLTA3NjAtNDA3MC1iY2I0LTBmMDBjZTNjNmI1ZCJd>)