Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
Feng Zhu, David Simchi-Levi
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an adaptive variance-inflation scheme for Thompson Sampling to improve efficiency, safety of regret distribution, and robustness to model mis-specification in bandits.
Problem
Thompson Sampling can perform poorly under stringent safety criteria (safety of cumulative regret distribution) and robustness to model mis-specification, despite strong average-case performance and guarantees.
Approach
Adaptively inflates the posterior variance used in Thompson Sampling to balance exploration, aiming to improve regret safety and robustness while preserving efficiency; details are not available beyond the abstract.
Experimental setup
Metrics: cumulative regret regret distribution
Builds on: Thompson Sampling
Closest papers by meaning
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.90)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.90)
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes (NeurIPS 2025 · similarity 0.89)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.89)
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.87)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.87)
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.
