Variance-sensitive Thompson sampling for generalised linear bandits, revisited
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
arXiv:2606.00431v1 Announce Type: new
Abstract: 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.
More from arXiv — Machine Learning
-
BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
Jun 2
-
DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions
Jun 2
-
Hoeffding Concept Bottleneck Models with Applications to Overhead Images
Jun 2
-
From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
Jun 2
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.