AI Paper Atlas

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

On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models

Emilie Kaufmann, Olivier Cappé, Aurélien Garivier

JMLR 2016 · Bandits and online learning › Multi-armed bandits · approach: Best-arm identification in linear bandits · 797 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 exploration rate log((log t +1)/delta) instead of log(t/delta) in elimination (ablation)Elimination algorithm · Gaussian two-armed, difficult modelrunning time at comparable error: about three times longerImproved
use exploration rate log((log t +1)/delta) instead of log(1/delta) (ablation)Elimination algorithm · Gaussian two-armed difficult modelempirical error probability vs deltaImproved
use SGLRT stopping rule instead of 1/2-EliminationBernoulli bandit model 0.2 vs 0.1 · sample complexitysamplesImproved
use SGLRT stopping rule instead of 1/2-EliminationBernoulli bandit model 0.51 vs 0.5 · sample complexitysamplesNo clear effect
use fixed-budget instead of fixed-confidence algorithm for same error probabilityTwo-armed bandits · number of samplessamples: about twice largerImproved

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