AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Learning Structured Distributions From Untrusted Batches: Faster and Simpler

Sitan Chen, Jerry Li, Ankur Moitra

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use LearnWithFilter with piecewise-constant post-processing for structured distributionsLearning from untrusted batches · Synthetic structured distributions, total variationestimation errorImproved
Increase batch size kLearnWithFilter and the oracle estimator · Synthetic arbitrary distributions, A_{ℓ/2} normestimation errorImproved
Increase batch size kNaive empirical mean · Synthetic arbitrary distributions, A_{ℓ/2} normestimation errorNo clear effect
Increase corruption fraction εNaive empirical mean · Synthetic arbitrary distributions, A_{ℓ/2} normestimation errorHurt
Vary domain size n while keeping the batch count independent of nLearnWithFilter · Synthetic arbitrary distributions, A_{ℓ/2} normestimation errorNo clear effect
Use the structured estimator instead of the empirical mean of uncorrupted samplesLearning structured distributions · Synthetic structured distributions, total variationestimation errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy