AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Simple and near-optimal algorithms for hidden stratification and multi-group learning

Christopher J Tosh, Daniel Hsu

ICML 2022 · Learning theory and algorithms › Fairness · approach: Minimax fairness via sampling · 0 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
Replace suboptimal decision-list PREPEND learner with sleeping-experts reduction (MLC-HEDGE based) for multi-group learningmulti-group agnostic learning · theoretical per-group excess risk boundper-group excess conditional risk rateImproved
Restrict group-realizable setting to ERM-per-group majority vote predictor (no sample splitting or complex reweighting)group-realizable multi-group learning · theoretical per-group conditional zero-one riskper-group excess risk rateNo clear effect
Use evaluation-function (order-1) scoring to order group-hypothesis pairs for decision listsmulti-group learning decision lists · two-distribution counterexampleworst-case per-group excess conditional risk: at least 1/8 excess riskHurt
Use the group-realizable majority-vote predictor (Algorithm 3) for general agnostic multi-group learningagnostic multi-group learning · constructed distribution with three groupsper-group excess zero-one risk: some group has excess risk > 1/4Hurt
Replace log|H| dependence in sleeping-experts reduction with pseudo-dimension of loss-composed class via ERM on half the data per groupAlgorithm 2 (sleeping experts reduction) · theoretical per-group risk boundper-group excess risk rateNo clear effect

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