stat.MLSep 2, 2026

Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling

Authors: Prateek JaiswalDebdeep PatiAnirban BhattacharyaBani K. Mallick

Organizations: Daniels School of Business, Purdue University. · Department of Statistics, University of Wisconsin-Madison. · Department of Statistics, Texas A&M University.

Abstract

We study a variant of the Thompson Sampling (TS) algorithm, called αα-TS, for solving stochastic generalized linear bandit problems. Existing analyses of TS require inflating the posterior variance to derive near-optimal regret guarantees. We formalize the idea of variance inflation by introducing αα-TS that uses a fractional or αα-posterior instead of the standard posterior. Our main contribution is to identify general regularity conditions on the prior and reward distributions that enable a regret analysis of αα-TS without assuming any tractable approximation of the posterior distribution, unlike previous works. For a specific choice of αd1α\propto d^{-1}, our general regret bound yields the best known regret bound of O(d3/2TlogT)O(d^{3/2}\sqrt{T}\log T) for both the exponential and sub-Gaussian families of reward distributions. We further provide an αα-dependent lower bound showing that the regret constant depends on the product αdαd, and that when αd1α\propto d^{-1} the regret scales as Ω(d3/2T)Ω(d^{3/2}\sqrt{T}), explaining the origin of the d3/2d^{3/2} factor in the upper bound. Our proof technique adapts and combines recent advancements in the analysis of linear bandit problems with first- and second-order posterior concentration theory from the Bayesian statistics literature.

Explore similar work

CardsList