# Estimator

Estimator is a high-level TensorFlow API whose classes support machine-learning model training, evaluation, prediction, and serving export.

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

## Trusting the Untestable: Validation and Diagnostics for the Doubly Robust Models

DevFeed: [Trusting the Untestable: Validation and Diagnostics for the Doubly Robust Models](<https://devfeed.tech/articles/trusting-the-untestable-validation-and-diagnostics-for-the-doubly-robust-models-1244.md>)

Original publisher: [Read original article](<https://eng.lyft.com/trusting-the-untestable-validation-and-diagnostics-for-the-doubly-robust-models-00853df009df?source=rss----25cd379abb8---4>)

Author: Shima Nassiri

Published: 2026-02-12T17:07:13Z

Content type: article

Language: en

Sources: [Lyft Engineering - Medium](<https://devfeed.tech/sources/lyft-engineering-medium.md>)

Topics: [Estimator](<https://devfeed.tech/topics/estimator.md>), [data](<https://devfeed.tech/topics/data.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>)

Tags: [aipw](<https://devfeed.tech/tags/aipw.md>), [doubleml](<https://devfeed.tech/tags/doubleml.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [lyft](<https://devfeed.tech/tags/lyft.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [models](<https://devfeed.tech/tags/models.md>), [quasi-experiment](<https://devfeed.tech/tags/quasi-experiment.md>), [rideshare](<https://devfeed.tech/tags/rideshare.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

The article explains how Lyft uses quasi-experimental methods to measure causal effects when randomized A/B tests are impractical. It focuses on Augmented Inverse Propensity Weighting (AIPW), a doubly robust estimator that uses outcome and propensity-score models to estimate treatment effects from non-randomized data.

### Source excerpt

written by Ross Chu and Shima Nassiri The Causal Frontier: Measurement Beyond Randomization The gold standard for determining the causal impact of a policy or product change at a company like Lyft is the A/B test (randomized experiment). By randomly assigning users to a treatment or control group, A/B tests inherently eliminate bias, providing clean estimates of the Average Treatment Effect (ATE). However, many critical business questions and large-scale initiatives simply cannot be randomized. This forces scientists to move past traditional experimentation and leverage quasi-experimental methods. We rely on non-randomized measurement in several key scenarios across Lyft: Partnerships and Policies: Assessing the incremental impact of a partnership (e.g., linking two company accounts) is often a non-randomized assignment. Since these collaborations require coordinated operational work across both companies and are typically announced or promoted broadly, this makes controlled randomization impractical. Long-Term Effect (LTE): Measuring effects that unfold over a long period, like the LTE of high prices on future rides, is typically handled by observational studies. Post-Launch Evaluation: Continuous monitoring of a policy after it has been fully rolled out requires a method that doesn't involve costly holdout groups or degradation tests. Biased Data: In cases where pre-existing experimental data is found to have an imbalance, a quasi-experimental approach can potentially leverage the biased data instead of requiring a costly rerun. Introducing Doubly Robust Models: Causal Inference Without Randomness To address these non-randomized measurement needs, Lyft relies on various quasi-experiment estimators. In this blog we specifically focus on using the Augmented Inverse Propensity Weighting (AIPW) model. This model was first established at Lyft to measure the impact of a negative user experience on future topline metrics like rides and bookings; AIPW is a form of doubly

## Estimating the Security of Ring Learning with Errors (RLWE)

DevFeed: [Estimating the Security of Ring Learning with Errors (RLWE)](<https://devfeed.tech/articles/estimating-the-security-of-ring-learning-with-errors-rlwe-40461.md>)

Original publisher: [Read original article](<https://www.jeremykun.com/2022/12/28/estimating-the-security-of-ring-learning-with-errors-rlwe/>)

Published: 2022-12-28T14:52:01Z

Content type: tutorial

Language: en

Sources: [Jeremy Kun](<https://devfeed.tech/sources/jeremy-kun.md>)

Topics: [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [Security](<https://devfeed.tech/topics/security.md>), [Estimator](<https://devfeed.tech/topics/estimator.md>), [FHE](<https://devfeed.tech/topics/fhe.md>)

Tags: [cod](<https://devfeed.tech/tags/cod.md>), [cryptography](<https://devfeed.tech/tags/cryptography.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [lattice-cryptography](<https://devfeed.tech/tags/lattice-cryptography.md>), [learning-with-errors](<https://devfeed.tech/tags/learning-with-errors.md>), [lwe](<https://devfeed.tech/tags/lwe.md>), [mathematics](<https://devfeed.tech/tags/mathematics.md>), [programming](<https://devfeed.tech/tags/programming.md>), [ring-learning-with-errors](<https://devfeed.tech/tags/ring-learning-with-errors.md>), [rlwe](<https://devfeed.tech/tags/rlwe.md>), [sage](<https://devfeed.tech/tags/sage.md>), [security](<https://devfeed.tech/tags/security.md>), [test](<https://devfeed.tech/tags/test.md>), [top](<https://devfeed.tech/tags/top.md>)

### AI overview

The article explains how to estimate the security of lattice-based schemes based on Learning With Errors (LWE) and Ring Learning With Errors (RLWE). It introduces LWE parameters and describes how the Lattice Estimator estimates the costs of known lattice attacks for a given instance.

### Source excerpt

This article was written by my colleague, Cathie Yun. Cathie is an applied cryptographer and security engineer, currently working with me to make fully homomorphic encryption a reality at Google. She's also done a lot of cool stuff with zero knowledge proofs. In previous articles, we've discussed techniques used in Fully Homomorphic Encryption (FHE) schemes. The basis for many FHE schemes, as well as other privacy-preserving protocols, is the Learning With Errors (LWE) problem.