Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits
Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
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 |
|---|---|---|---|
| Measure information gained about the hidden parameter instead of the round-specific optimal action | Thompson Sampling · Contextual bandits with adversarially selected contexts | Bayesian regret: R_T \le \sqrt{\rho TH(\theta^*)} | Improved |
| Use the lifted information ratio for logistic bandits with Lipschitz logits | Thompson Sampling · Logistic bandits with linear logits | Bayesian regret: R_T \le \sqrt{2KT\left(d\log(2SBT+1)+1\right)} = \widetilde{O}\big(\sqrt{dKT}\big) | Improved |
Closest papers by meaning
- Contextual Thompson Sampling via Generation of Missing Data (NeurIPS 2025 · similarity 0.90)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.90)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.90)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.90)
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions (NeurIPS 2026 · similarity 0.89)
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.
