AI Paper Atlas

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

Batched Dueling Bandits

Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan

ICML 2022 · Bandits and online learning › Multi-armed bandits · approach: Non-stationary and structured-reward bandits · 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
Use a seed set and eliminate active arms through seed comparisons instead of all-pairs comparisons initiallySCOMP · Batched dueling bandits, SST + STIinstance-dependent expected regret: 3KT^{1/B} \log\left(6TK^2B\right) \sum_{j: \epsilon_{j} > 0} \frac{1}{\epsilon_{j}} -> \sum_{j: \epsilon_{j} > 0}O\left(Improved
Add a candidate-selection round among seed arms before eliminating active arms (ablation)SCOMP2 · Batched dueling bandits, SST + STIworst-case expected regret: O\left(\frac{K\sqrt{K}T^{1/B}\log(T)}{\epsilon_{\min}}\right) -> O\left(\frac{KBT^{1/B} \log(T)}{\epsilon_{\min}}\right)Improved
Reduce seed inclusion probability from 1/√K to K^{-2/3} (ablation)SCOMP · Batched dueling bandits, SST + STIworst-case expected regret: O\left(\frac{K\sqrt{K}T^{1/B}\log(T)}{\epsilon_{\min}}\right) -> O\left(\frac{K^{4/3}T^{1/B}\log(T)}{\epsilon_{\min}}\riImproved
Add recursive rounds and use a seed set of size K^η (ablation)Recursive seeded algorithm · Batched dueling bandits, SST + STIinstance-dependent expected regret: B+2: K^{0.39} \,\, T^{1/B} \,\, \log(T) \,\, E; B+3: K^{0.32} \,\, T^{1/B} \,\, \log(T) \,\, E; B+5: K^{0.25} \,\, T^{1/Improved
Increase the number of batches B (ablation)SCOMP2 · Six rankers, Sushi, SYN-BTL, SYN-CDcumulative regretImproved
Use SCOMP2 rather than BTMBatched dueling bandits · Six rankers, Sushi, SYN-BTL, SYN-CDcumulative regretImproved
Use SCOMP2 rather than RUCBBatched dueling bandits · Six rankers, Sushi, SYN-BTL, SYN-CDcumulative regret: 3 out of the 4 datasetsMixed
Use PCOMP or SCOMP rather than BTMBatched dueling bandits · Six rankers and Sushicumulative regretImproved
Use PCOMP or SCOMP rather than BTMBatched dueling bandits · Synthetic datacumulative regretMixed
Increase the number of batches for SCOMP2 (ablation)SCOMP2 · SYN-BTLcumulative regretImproved

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