AI Paper Atlas

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

Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost

Yu-Jie Zhang, Masashi Sugiyama

NeurIPS 2023 · Bandits and online learning › Online convex optimization and games · approach: Best-of-both-worlds bandit algorithms · 0 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 OFU-MLogB with constant per-round cost instead of MNL-UCBmultinomial logistic bandit · Multinomial logistic bandit, T=3000running time: around 50 times fasterImproved
Use OFU-MLogB instead of MNL-UCBmultinomial logistic bandit · Multinomial logistic bandit, T=3000empirical regretImproved
Use OFU-MLogB instead of ada-OFU-ECOLogbinary logistic bandit · Binary logistic bandit, T=3000, S=5computation overheadImproved
Use OFU-MLogB instead of ada-OFU-ECOLogbinary logistic bandit · Binary logistic bandit, T=3000, S=5regretNo clear effect
Use OFU-MLogB instead of O2LMbinary logistic bandit · Binary logistic bandit, T=3000time per iterationNo clear effect

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