Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Improved Optimistic Algorithms for Logistic Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace the uniform prediction-error analysis with a local analysis using the sigmoid curvature and a Bernstein-like self-normalized martingale inequality | GLM-UCB improved · Logistic bandit | regret upper bound: \mcal{O}\left({\color{black}\pmb{\kappa}}\cdot d \cdot T^{1/2}\cdot \log(T)^{3/2}\right) -> \mcal{O}\left({\color{black} | Helped |
| Use a local first-order prediction bound and push the κ dependence into a second-order term, with admissible log-odds constraints | OurBandit · Logistic bandit | regret upper bound: \mcal{O}\left({\color{black}\pmb{\kappa^{1/2}}}\cdot d \cdot T^{1/2} \log(T)\right) -> \mcal{O}\left( d \cdot T^{1/2} \l | Helped |
Closest papers by meaning
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions (NeurIPS 2026 · similarity 0.91)
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.90)
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · similarity 0.89)
- Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards (NeurIPS 2025 · similarity 0.89)
- Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit (NeurIPS 2024 · similarity 0.89)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · 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.