AI Paper Atlas

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

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits

Mengmeng Li, Philipp J. Schneider, Jelisaveta Aleksic, Daniel Kuhn

ICLR 2026 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Oracle-efficient contextual bandits

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
replace Newton-method projection with bisection on the KKT-derived 1-D root-finding problemFTRL/OSMD m-set projection · per-iteration runtime, m=5, K=100runtime: nearly 10 times fasterImproved
replace direct MOSEK solve of the projection with bisectionFTRL/OSMD m-set projection · per-iteration runtime, m=5, K from 10 to 100runtime: approximately 5 times fasterImproved
use Shannon-entropy regularizer instead of hybrid regularizerscontextual combinatorial FTRL · adversarial regretregret bound: extra log T term in adversarial regretHurt

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