AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Sharp uniform convergence bounds through empirical centralization

Cyrus Cousins, Matteo Riondato

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates · 4 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 empirical centralization of the function family instead of non-centralized boundsSupremum deviation bounds · Synthetic distributions in R^d, m up to 10^7, delta=0.01SD bound tightnessImproved
Use empirical centralization at very small sample sizes (all bounds vacuous)Supremum deviation bounds · Synthetic distributions, small mSD bound tightnessHurt
Monte-Carlo estimate of ERA with n=32 trials instead of analytical ERA boundCentralized SD bound · Synthetic distributionsSD bound tightnessImproved
Increase dimension d from 4 to 256 for family F1MC-ERA bound · F1 experimentsMC-ERA magnitudeHurt
Increase number of Monte-Carlo trials nMC-ERA to ERA gap · Synthetic distributionsbound gapImproved

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