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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use OFU-MLogB with constant per-round cost instead of MNL-UCB | multinomial logistic bandit · Multinomial logistic bandit, T=3000 | running time: around 50 times faster | Improved |
| Use OFU-MLogB instead of MNL-UCB | multinomial logistic bandit · Multinomial logistic bandit, T=3000 | empirical regret | Improved |
| Use OFU-MLogB instead of ada-OFU-ECOLog | binary logistic bandit · Binary logistic bandit, T=3000, S=5 | computation overhead | Improved |
| Use OFU-MLogB instead of ada-OFU-ECOLog | binary logistic bandit · Binary logistic bandit, T=3000, S=5 | regret | No clear effect |
| Use OFU-MLogB instead of O2LM | binary logistic bandit · Binary logistic bandit, T=3000 | time per iteration | No clear effect |
Closest papers by meaning
- Improved Optimistic Algorithms for Logistic Bandits (ICML 2020 · similarity 0.92)
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.91)
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions (NeurIPS 2026 · similarity 0.90)
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · similarity 0.89)
- Combinatorial Reinforcement Learning with Preference Feedback (ICML 2025 · similarity 0.88)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.88)
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.
