AI Paper Atlas

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

Bayesian decision-making under misspecified priors with applications to meta-learning

Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire

NeurIPS 2021 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Thompson sampling analysis · 9 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
meta-learn the prior (MetaTS:full) instead of using a misspecified N(0,I) priorGaussian Thompson sampling · Gaussian MAB (6 arms, H=10)cumulative average per-episode rewardImproved
also meta-learn prior covariance, not just the prior mean (ablation)MetaTS · Gaussian MAB (6 arms, H=10)per-episode rewardImproved
meta-learn the prior in Gaussian linear contextual banditGaussian linear TS · Gaussian linear contextual bandit (H=20)per-episode rewardImproved
use Knowledge Gradient (2-RHC) as base learner instead of Thompson samplingBayesian meta-learner · Discrete bandits (20 arms, 16 tasks)per-episode rewardImproved

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