AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Connections Between Mirror Descent, Thompson Sampling and the Information Ratio

Julian Zimmert, Tor Lattimore

NeurIPS 2019 · Bandits and online learning › Online convex optimization and games · approach: Online learning with feedback graphs · 11 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 the shifted importance-weighted estimator instead of the standard estimator (ablation)OSMD with the 1/2-Tsallis entropy potential · Adversarial k-armed banditsregret: \sqrt{8nk} -> \sqrt{2 k n} + 48kImproved
Use a clipped separable potential instead of prior potentialsOSMD · Online linear optimization over \ell_p-balls, full informationregret: \mathcal O\left(\sqrt{\min\left\{1 / (p-1),\log(d)\right\}n}\right)Improved
Transfer OSMD stability analysis to modified Thompson sampling with a Bayesian updateModified Thompson sampling · Bayesian online learningBayesian 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