AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Near-Optimal Confidence Sequences for Bounded Random Variables

Arun K Kuchibhotla, Qinqing Zheng

ICML 2021 · Bandits and online learning › Multi-armed bandits · approach: Bandit formulations for ML problems · 2 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 classical concentration-based confidence sequences with Bentkus confidence sequencesAdaptive mean estimation · Bounded-mean data generated as averages of m uniform samplesstopping-time ratio to second best: 0.79, 0.66, 0.72, 0.86, 0.84Improved
Replace A-Hoeffding confidence sequences with A-Bentkus confidence sequencesBest-arm identification algorithm · Bernoulli-reward best-arm identificationsample count: 52% to 61%Improved
Use Bentkus rather than classical confidence sequencesConfidence sequences for the mean · Bernoulli(0.1), typically n ≥ 20confidence interval widthImproved
Use Bentkus rather than A-HoeffdingConfidence sequences for the mean · Bernoulli(0.5), moderate to large sample sizesconfidence interval widthImproved
Use Bentkus rather than A-HoeffdingConfidence sequences for the mean · Bernoulli(0.5), moderate to large sample sizesconfidence interval widthNo clear effect
Truncate confidence intervals to [0, 1] (ablation)A-Hoeffding in best-arm identification · Best-arm identification, K = 2iterations: 107 -> 132Hurt
Use cumulative minimum/maximum bounds to define the sampling radius (ablation)A-Bentkus in best-arm identification · Best-arm identificationsample complexityHurt
Use Bernstein-type confidence sequences instead of A-HoeffdingBest-arm identification algorithm · Best-arm identificationsample complexityHurt
Use the A-Bentkus methodConfidence sequences for the mean · Bernoulli(0.1), 1000 replicationsmiscoverage rate: 0.001No clear effect
Use a faster-growing stitching function h(k) (ablation)A-Bentkus confidence sequence · Bounded random variablesconfidence interval widthHurt

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