AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

On the Equivalence between Online and Private Learnability beyond Binary Classification

Young Jung, Baekjin Kim, Ambuj Tewari

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Robust and surrogate-loss learning bounds · 3 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
Assume private PAC learnabilityMulti-class classification · Multi-class classificationonline learnabilityImproved
Assume private PAC learnabilityRegression · Regressiononline learnabilityImproved
Use global stability as an intermediate stepOnline-learnable multi-class classes · Multi-class classificationprivate learnabilityImproved
Use tolerance-based Littlestone dimension and relaxed zero-one loss to connect discretized regression to multi-class learningRegression classes · Regressiononline learnability characterizationImproved
Require a finite class or finite input domainOnline-learnable regression classes · Regressionprivate learnabilityImproved
Require a finite range over the input domainOnline-learnable regression classes · Regressionprivate learnabilityImproved
Require finite sup-norm covers at every scaleOnline-learnable regression classes · Regressionprivate learnabilityImproved
Require finite sequential Pollard pseudo-dimensionOnline-learnable regression classes · Regressionprivate learnabilityImproved
Apply the global-stability and stable-histogram proof strategy directly to real-valued regressionOnline-learnable regression classes · Regressionprivate learnability equivalenceNo 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