AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: PAC learnability theory · 1 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
Characterize realizable PAC learnability using the scaled OIG dimensionReal-valued hypothesis classes · Realizable PAC regressionPAC learnabilityImproved
Use a deterministic learner guided by the online dimensionReal-valued hypothesis classes · Realizable online regressionexpected cumulative loss: \mathfrak{C}_\infty \leq \mathbb{D}^\mathrm{onl}(\mathcal{H}) + \epsilon; lower bound: \mathfrak{C}_\infty \geq \mathbb{Improved
Characterize worst-case ERM learnability using the scaled Graph dimensionReal-valued hypothesis classes · Realizable PAC regression by any ERMPAC learnabilityImproved
Require finite scaled DS dimension as a necessary conditionReal-valued hypothesis classes · Realizable PAC regressionPAC learnabilityImproved
Use finite fat-shattering dimension as a learnability criterionReal-valued hypothesis classes · Realizable PAC regressionPAC learnabilityNo clear effect
Assume finite scaled DS dimension is sufficient for learnabilityReal-valued hypothesis classes · Realizable PAC regressionPAC learnabilityMixed

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