AI Paper Atlas

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

Efficient Pure Exploration in Adaptive Round model

Tianyuan Jin, Jieming SHI, Xiaokui Xiao, Enhong Chen

NeurIPS 2019 · Bandits and online learning › Multi-armed bandits · approach: Pure exploration algorithms · 8 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
delta-E instead of MEdelta-E · PAC best armquery cost: 100 timesImproved
delta-ER (R=2 rounds) instead of MEdelta-ER · PAC best armquery cost: 10 timesImproved
hard round limit R=2 (delta-ER) vs no limit (delta-E)delta-ER · PAC best armquery cost: 100 times -> 10 timesHurt
delta-E instead of ME in roundsdelta-E · PAC best armrounds: 11 -> 2.2Improved
k-delta-ER instead of ME-ASk-delta-ER · PAC top-20query cost: 100 timesImproved
k-delta-E instead of ME-ASk-delta-E · PAC top-20query cost: 1000 timesImproved
k-delta-E instead of ME-AS in roundsk-delta-E · PAC top-20rounds: 6 -> 2.1Improved
EG-delta-E instead of Elimination [8]EG-delta-E · Exact top-kquery cost: 250 timesImproved
EG-delta-E instead of Elimination [8] in roundsEG-delta-E · Exact top-k Normalrounds: 36 -> 21Improved
EG-delta-E instead of UCB [17]EG-delta-E · Exact top-kquery costNo 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