AI Paper Atlas

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

No Regrets for Learning the Prior in Bandits

Soumya Basu, Branislav Kveton, Manzil Zaheer, Csaba Szepesvari

NeurIPS 2021 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Thompson sampling analysis · 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
Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each taskThompson sampling for sequential bandit tasks · Gaussian bandit, σq = 0.5cumulative regret: about 30% lowerImproved
Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each taskThompson sampling for sequential bandit tasks · Gaussian bandit, σq = 1cumulative regretImproved
Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each taskThompson sampling for sequential bandit tasks · Linear bandit, σq = 1cumulative regret: more than three times lower 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