AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Sharp Empirical Bernstein Inequalities for the Variance of Bounded Random Variables

Diego Martinez-Taboada, Aaditya Ramdas

ICML 2026 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates

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 Bernstein variance confidence intervals instead of Maurer-Pontil self-bounding intervalsvariance/std confidence intervals · batch setting, uniform(0,1), beta(2,6), beta(5,5)confidence interval widthImproved
replace the variance confidence sequences in adaptive Neyman allocation with the proposed upper confidence sequenceadaptive Neyman allocation (Neopane et al., 2025) · ATE sequential estimation, uniform and beta potential outcomesmean squared error of ATEImproved
estimate variance of squared deviations empirically instead of upper bounding it by sigma squared (ablation)variance confidence interval first-order width · asymptotic width, iid datafirst-order width: 2 sigma sqrt(2 log(2/alpha)) -> sqrt(2 V[(X-mu)^2] log(1/alpha))Improved
express variance as E[X^2] - mu^2 and apply bounded-variable inequalities to both moments with a union bound (ablation)variance confidence interval · theory and appendix comparisoninterval tightnessHurt
use alpha1 = alpha/log n split in lower interval for sharpness instead of equal split (ablation)lower confidence interval · asymptotic sharpnessfirst-order widthImproved

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