AI Paper Atlas

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

Covariance-adaptive best arm identification

El Mehdi Saad, Gilles Blanchard, Nicolas Verzelen

NeurIPS 2023 · Bandits and online learning › Multi-armed bandits · approach: Best-arm identification in linear bandits · 0 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 simultaneous observations and pairwise comparisons that estimate reward-difference variancePairwise-BAI · Bounded rewards, fixed-confidence best-arm identificationquery complexityImproved
Use simultaneous observations and pairwise comparisons that estimate reward-difference variancePairwise-BAI · Gaussian rewards, fixed-confidence best-arm identificationquery complexityImproved
Continue querying arms after they are eliminated from the candidate set (ablation)Pairwise-BAI · Bounded rewards, fixed-confidence best-arm identificationquery complexity guaranteeImproved
Stop querying eliminated arms rather than continuing to sample them (ablation)Pairwise-BAI · Gaussian rewards, fixed-confidence best-arm identificationquery complexity guaranteeHurt
Continue sampling eliminated arms until round 2t instead of round 82t (ablation)Pairwise-BAI+ · Synthetic Gaussian experimentsaverage sample complexityHurt
Remove the instruction to continue querying eliminated arms (ablation)Pairwise-BAI · Synthetic Gaussian experimentsaverage sample complexityImproved
Compare candidate arms with convex combinations of other arms rather than only pairwiseConvex-BAI · Bounded rewards, fixed-confidence best-arm identificationquery complexityImproved
Increase the number of highly correlated suboptimal armsPairwise-BAI and Pairwise-BAI+ · Synthetic Gaussian clustered-arm experimentaverage sample complexityImproved

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