AI Paper Atlas

Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework

Ziyi Huang, Henry Lam, Amirhossein Meisami, Haofeng Zhang

NeurIPS 2023 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Thompson sampling analysis · 2 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 EBUCB instead of BUCBBernoulli bandit with misspecified posteriors (P1, P2) · 2-armed Bernoulli bandit, w=0.9/0.8/0.7regretImproved
use EBUCB instead of Thompson samplingBernoulli bandit with misspecified posteriors (P1, P2) · 2-armed Bernoulli bandit, w=0.9/0.8/0.7regretImproved
drop the horizon-dependent term (c = 0) (ablation)EBUCB · 2-armed Bernoulli banditregretNo clear effect
increase inference error level r in worst-case posterior (ablation)Thompson sampling · worst-case misspecified posteriorregret slopeHurt
bound only one alpha-divergence of the posterior (ablation)BUCB/EBUCB · worst-case misspecified posteriorregretHurt

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