AI Paper Atlas

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

An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem

Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan

NeurIPS 2022 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 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 C2B with at most log(T) batches instead of fully sequential updatesK-armed dueling bandits under the Condorcet condition · Real-world preference datasetscumulative regretNo clear effect
Use C2B with B = floor(log(T)) batches instead of BTMDueling-bandit experiments · Six rankers, Sushi, Irish-Meath, Irish-Dublin, MSLR30, Yahoo30cumulative regretImproved
Use C2B with B = floor(log(T)) batches instead of SCOMP2Dueling-bandit experiments · Most tested datasetscumulative regretImproved
Use C2B with B = floor(log(T)) batches instead of RUCBDueling-bandit experiments · All datasets except Yahoo30cumulative regretNo clear effect
Use C2B with B = floor(log(T)) + 6 batches instead of RUCBDueling-bandit experiments · Six rankers, Sushi, Irish-Meath, Irish-Dublin, MSLR30, Yahoo30cumulative regretImproved
Use C2B with B = floor(log(T)) + 6 batches instead of RMEDDueling-bandit experiments · All datasets except Yahoo30cumulative regretNo clear effect
Increase C2B's batch count by a constant number of additional rounds (ablation)C2B · Real-world preference datasetscumulative regretImproved
Replace the elimination criterion with KL-divergence-based elimination (ablation)C2B · Computational experiments on real-world datasetscumulative regretImproved
Use a random seed-set selection strategySCOMP2 · Repeated runs on the same datasetcumulative regretMixed

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