# Amazon Machine Learning

A legacy AWS service for training and evaluating machine learning models and generating predictions.

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

## Replication of Thermal Comfort Cohort Models: No Support for Improved Thermal Preference Prediction

DevFeed: [Replication of Thermal Comfort Cohort Models: No Support for Improved Thermal Preference Prediction](<https://devfeed.tech/articles/replication-of-thermal-comfort-cohort-models-no-support-for-improved-thermal-preference-prediction-125526.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12178>)

Author: Thomas Hirsch, Katja Ceplak, Veronika Windisch, Samina Kadkhoda Masoumali, Matias Quintana, Clayton Miller, Stefano Schiavon, Gerald Schweiger

Published: 2026-11-10T05:00:00Z

Content type: news

Language: en

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

Topics: [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Amazon Machine Learning](<https://devfeed.tech/topics/amazon-machine-learning.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>)

Tags: [assessment](<https://devfeed.tech/tags/assessment.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cross-validation](<https://devfeed.tech/tags/cross-validation.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [information](<https://devfeed.tech/tags/information.md>), [metric](<https://devfeed.tech/tags/metric.md>), [models](<https://devfeed.tech/tags/models.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [original](<https://devfeed.tech/tags/original.md>), [performance](<https://devfeed.tech/tags/performance.md>), [personal](<https://devfeed.tech/tags/personal.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [random](<https://devfeed.tech/tags/random.md>), [replication](<https://devfeed.tech/tags/replication.md>), [thermal](<https://devfeed.tech/tags/thermal.md>)

### AI overview

The replication found no evidence that cohort comfort models (CCMs) improve thermal preference prediction over simple class-distribution baselines. On the DORN dataset (20 participants, six months) and an independent PersonAI dataset (72 participants, four weeks), a majority-class predictor matched CCMs on F1-micro; on F1-macro, CCMs had lower median scores than random predictions based on estimated preference distributions. The authors identify limited observations, class imbalance, missing trivial baselines, inadequate cross-validation, and information leakage as problems in the original study. They recommend better-designed studies, including controlled thermal conditions, to gather enough observations across preference classes.

### Source excerpt

arXiv:2611.12178v1 Announce Type: new Abstract: Cohort comfort models (CCMs) aim to overcome the extensive individual data requirements of personal comfort models (PCMs) by grouping occupants based on demographic and psychometric characteristics (cold start) or similar thermal preferences (warm start). We evaluated the validity of the reported CCM performance gains through (i) a methodological assessment of the original study, (ii) a replication using one of the two original datasets (DORN: 20 participants, 6 months) under a revised experimental protocol, and (iii) a replication using an independently collected dataset (PersonAI: 72 participants, 4 weeks). Classification performance was evaluated using F1-micro, as in the original study, and F1-macro to account for class imbalance. Under F1-micro, a trivial baseline that always outputs the majority class performed on par with cohort models. Under F1-macro, all cohort models achieved lower median scores than a simple baseline that makes random predictions based on the estimated distribution of thermal preferences. In our methodological assessment we identified the following key issues: Limited data per participant and per minority class, reliance on a metric insensitive to class imbalance, missing trivial baselines, inadequate cross validation strategy, and multiple occurrences of information leakage. Our findings challenge the original study's conclusion that CCMs improve thermal preference prediction. CCMs did not outperform simple class-distribution baselines. Future studies should improve experimental designs, including controlled thermal conditions, to obtain sufficient observations across thermal preference classes.

## Partial Invariance for Classification under Structural Causal Models

DevFeed: [Partial Invariance for Classification under Structural Causal Models](<https://devfeed.tech/articles/partial-invariance-for-classification-under-structural-causal-models-114672.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02254>)

Author: Austin Goddard, Yu Xiang

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [Amazon Machine Learning](<https://devfeed.tech/topics/amazon-machine-learning.md>), [Inference](<https://devfeed.tech/topics/inference.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [environment](<https://devfeed.tech/tags/environment.md>), [environments](<https://devfeed.tech/tags/environments.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [features](<https://devfeed.tech/tags/features.md>), [invariance](<https://devfeed.tech/tags/invariance.md>), [light](<https://devfeed.tech/tags/light.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [risk](<https://devfeed.tech/tags/risk.md>), [sample](<https://devfeed.tech/tags/sample.md>), [stat-me](<https://devfeed.tech/tags/stat-me.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [target](<https://devfeed.tech/tags/target.md>), [test](<https://devfeed.tech/tags/test.md>), [training](<https://devfeed.tech/tags/training.md>), [tunnel](<https://devfeed.tech/tags/tunnel.md>), [using](<https://devfeed.tech/tags/using.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The paper introduces environment-label separation, a partial invariance that splits the target conditional distribution into an environment-invariant and a label-invariant component. With labeled data from training environments and unlabeled test features, this structure can support estimating the target distribution in an unseen environment. In a structural causal model framework, the authors give sufficient conditions for the separation and propose dIMP-Classifier, which jointly minimizes estimated test risk and encourages cross-environment invariance. Their finite-sample guarantees relate test risk to deviations from invariance, estimation error, and sample complexity. Simulated experiments and tests on the light tunnel Causal Chamber data report performance under interventions on the target mechanism and consistent gains over the standard and invariance-based baselines considered.

### Source excerpt

arXiv:2611.02254v1 Announce Type: cross Abstract: Making predictions in an unseen environment from data collected across multiple training environments is challenging. This challenge is particularly pronounced when the target-generating mechanism varies across environments. In this work, we introduce environment-label separation, a form of partial environmental invariance that decomposes the target conditional distribution into an environment-invariant component and a label-invariant component. We show that this partial invariance enables estimation of the target conditional distribution in an unseen environment when using labeled training data together with unlabeled test features. Within the structural causal model framework, we provide sufficient conditions for environment-label separation. Building on these conditions, we develop an algorithm, dIMP-Classifier, which jointly minimizes an estimate of the test risk and encourages invariance across environments. We further provide finite-sample guarantees that characterize the test risk in terms of deviations from invariance, estimation error, and sample complexity. Experiments on simulated data and the real-world light tunnel Causal Chamber data demonstrate that the proposed approach can perform under interventions on the target mechanism and consistently outperforms the considered standard and invariance-based baselines.

## Building a Minimal Control Plane to Reconcile Docker Containers for Model Serving

DevFeed: [Building a Minimal Control Plane to Reconcile Docker Containers for Model Serving](<https://devfeed.tech/articles/i-killed-a-container-and-it-came-back-40144.md>)

Original publisher: [Read original article](<https://korbonits.com/blog/2026-07-02-i-killed-a-container-and-it-came-back/>)

Published: 2026-07-02T00:00:00Z

Content type: tutorial

Language: en

Sources: [Alex Korbonits](<https://devfeed.tech/sources/alex-korbonits.md>)

Topics: [control-plane](<https://devfeed.tech/topics/control-plane.md>), [model-serving](<https://devfeed.tech/topics/model-serving.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [Amazon Machine Learning](<https://devfeed.tech/topics/amazon-machine-learning.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [container](<https://devfeed.tech/tags/container.md>), [control-plane](<https://devfeed.tech/tags/control-plane.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model-serving](<https://devfeed.tech/tags/model-serving.md>), [python](<https://devfeed.tech/tags/python.md>)

### AI overview

The author explains control planes by building a small Python-based system that maintains a declared number of Docker containers for model serving. The system repeatedly compares desired and actual state and reconciles differences, including restoring a container after it stops.

### Source excerpt

I can design batch, real-time, and streaming inference -- the data plane. But I'd never built the control plane that manages it. So I built the smallest one I could, from scratch, to finally understand reconciliation: the one idea that separates a control plane from a deploy script.