Variance-sensitive Thompson sampling for generalised linear bandits, revisited
Not on the map. Why?
Abstract (arXiv)
We prove a variance-sensitive regret bound for Thompson sampling in stochastic generalised linear bandits. The argument assumes a warm-up, after which the regret is controlled through using the Gaussian Poincar'e inequality. This bypasses the point at which previous optimism-based analyses break down. Removing the warm-up while retaining the same variance-sensitive scaling remains open, and appears nontrivial.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 24 references that are in the map. First posted on arXiv 29 May 2026.
Builds on
10 of 24 references.
References · 10
- 2017A Tutorial on Thompson Samplingcited by 433
- 2020Improved Optimistic Algorithms for Logistic Banditscited by 118
- 2017Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Spacecited by 76
- 2019Randomized Exploration in Generalized Linear Banditscited by 70
- 2022Jointly Efficient and Optimal Algorithms for Logistic Banditscited by 41
- 2020Self-Concordant Analysis of Generalized Linear Bandits with Forgettingcited by 29
- 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Banditscited by 29
- 2025Generalized Linear Bandits: Almost Optimal Regret with One-Pass Updatecited by 16
- 2023Exploration via linearly perturbed loss minimisationcited by 13
- 2025When and why randomised exploration works (in linear bandits)cited by 8
Built on by
Not cited yet.