AI Paper Atlas

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

On Elimination Strategies for Bandit Fixed-Confidence Identification

Andrea Tirinzoni, Rémy Degenne

NeurIPS 2022 · Bandits and online learning › Multi-armed bandits · approach: Pure exploration algorithms · 1 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
add elimination stopping instead of LLR stopping (ablation)LinGame · linear BAIsamples: 45.34 -> 43.67Improved
add elimination at sampling and stopping (ablation)LinGame · linear BAIsamples: 45.34 -> 32.49Improved
add elimination at sampling and stopping (ablation)FWS · linear BAItime per iteration (ms): 0.73 -> 0.45 (-38%)Improved
add elimination at sampling and stopping (ablation)LinGapE · linear BAIsamples: 33.19 -> 29.89Improved
add elimination at sampling and stopping (ablation)FWS · linear Top-mtime per iteration (ms): 3.0 -> 0.97 (-67%)Improved
add elimination at sampling and stopping (ablation)FWS · linear Top-msamples: 78.28 -> 77.79No clear effect
add elimination at sampling and stopping (ablation)MisLid · linear Top-msamples: 87.77 -> 69.58Improved
add elimination at sampling and stopping (ablation)LinGame · linear OSIsamples: 23.77 -> 14.87Improved
add elimination at sampling and stopping (ablation)FWS · linear OSIsamples: 15.26 -> 14.99No clear effect
add elimination stopping only (no sampling elimination) (ablation)FWS · linear BAIsamples: 42.26 -> 42.25No clear effect
add elimination at sampling and stopping (ablation)Lazy TaS · linear Top-mtime per iteration (ms): 0.57 -> 0.36 (-36%)Improved
full elimination instead of selective elimination (ablation)LinGame · linear BAIstopping timeNo clear effect

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