Research map / Bandits and online learning / Contextual bandits and Thompson sampling
UCB-based Algorithms for Multinomial Logistic Regression Bandits
Sanae Amani, Christos Thrampoulidis
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 |
|---|---|---|---|
| increase number of outcomes K from 1 to 3 | MNL-UCB · synthetic MNL bandit (d=2, T=1000, 20 arms) | average regret | Hurt |
| increase kappa upper bound from 30 to 60 to 100 (K=2) | MNL-UCB · synthetic MNL bandit (K=2) | average regret | Hurt |
| use the locally adaptive estimator and bonus instead of the global-bound tilde estimator and bonus (ablation) | MNL-UCB · synthetic MNL bandit (K=2, kappa=30) | average regret | Improved |
Closest papers by meaning
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · similarity 0.91)
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.91)
- Multinomial Logit Contextual Bandits: Provable Optimality and Practicality (AAAI 2021 · similarity 0.91)
- Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities (NeurIPS 2025 · similarity 0.89)
- Contextual Multinomial Logit Bandits with General Value Functions (NeurIPS 2024 · similarity 0.89)
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions (NeurIPS 2026 · 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.
