A Broader View of Thompson Sampling

• URL: http://arxiv.org/abs/2510.07208v1
• Date: Wed, 08 Oct 2025 16:43:02 GMT
• Title: A Broader View of Thompson Sampling
• Authors: Yanlin Qu, Hongseok Namkoong, Assaf Zeevi,
• Abstract summary: Thompson Sampling is one of the most widely used and studied bandit algorithms.<n>The exact mechanism through which Thompson Sampling is able to "properly" balance exploration and exploitation is a mystery.<n>This paper recasts Thompson Sampling as an online optimization algorithm.
• Score: 13.204555981031966
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid theoretical guarantees. Yet, in stark contrast to most other families of bandit algorithms, the exact mechanism through which posterior sampling (as introduced by Thompson) is able to "properly" balance exploration and exploitation, remains a mystery. In this paper we show that the core insight to address this question stems from recasting Thompson Sampling as an online optimization algorithm. To distill this, a key conceptual tool is introduced, which we refer to as "faithful" stationarization of the regret formulation. Essentially, the finite horizon dynamic optimization problem is converted into a stationary counterpart which "closely resembles" the original objective (in contrast, the classical infinite horizon discounted formulation, that leads to the Gittins index, alters the problem and objective in too significant a manner). The newly crafted time invariant objective can be studied using Bellman's principle which leads to a time invariant optimal policy. When viewed through this lens, Thompson Sampling admits a simple online optimization form that mimics the structure of the Bellman-optimal policy, and where greediness is regularized by a measure of residual uncertainty based on point-biserial correlation. This answers the question of how Thompson Sampling balances exploration-exploitation, and moreover, provides a principled framework to study and further improve Thompson's original idea.

Related papers

• Thompson Sampling via Fine-Tuning of LLMs [68.1722422968855]
  We propose an alternative based on Thompson sampling that eliminates the need for scalable large acquisition functions.<n>Our approach Thompson Sampling via Finening (ToSFiT) leverages the prior knowledge embedded in prompt-conditioned language models, and adapts incrementally toward the posterior.<n>Our analysis reveals the critical role of careful adaptation to the posterior probability of maximality-a principle that underpins our ToSFiT algorithm.
  arXiv  Detail & Related papers  (2025-10-15T09:13:59Z)
• Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget [55.938644481736446]
  We introduce a novel algorithm for best feasible arm identification that guarantees an exponential decay in the error probability.<n>We validate our algorithm through comprehensive empirical evaluations across various problem instances with different levels of complexity.
  arXiv  Detail & Related papers  (2025-06-03T02:56:26Z)
• Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits [17.11922027966447]
  This work provides theoretical guarantees of Thompson sampling in high dimensional and sparse contextual bandits. For faster computation, we use spike-and-slab prior to model the unknown parameter and variational inference instead of MCMC.
  arXiv  Detail & Related papers  (2022-11-11T02:23:39Z)
• Langevin Monte Carlo for Contextual Bandits [72.00524614312002]
  Langevin Monte Carlo Thompson Sampling (LMC-TS) is proposed to directly sample from the posterior distribution in contextual bandits. We prove that the proposed algorithm achieves the same sublinear regret bound as the best Thompson sampling algorithms for a special case of contextual bandits.
  arXiv  Detail & Related papers  (2022-06-22T17:58:23Z)
• Diffusion Approximations for Thompson Sampling in the Small Gap Regime [6.508628820027702]
  We study the process-level dynamics of Thompson sampling in the small gap'' regime.<n>We show that the process-level dynamics of Thompson sampling converge weakly to the solutions to certain differential equations and ordinary differential equations.
  arXiv  Detail & Related papers  (2021-05-19T16:28:01Z)
• Doubly-Adaptive Thompson Sampling for Multi-Armed and Contextual Bandits [28.504921333436833]
  We propose a variant of a Thompson sampling based algorithm that adaptively re-weighs the terms of a doubly robust estimator on the true mean reward of each arm. The proposed algorithm matches the optimal (minimax) regret rate and its empirical evaluation in a semi-synthetic experiment. We extend this approach to contextual bandits, where there are more sources of bias present apart from the adaptive data collection.
  arXiv  Detail & Related papers  (2021-02-25T22:29:25Z)
• Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring [91.22679787578438]
  We present a novel Thompson-sampling-based algorithm for partial monitoring. We prove that the new algorithm achieves the logarithmic problem-dependent expected pseudo-regret $mathrmO(log T)$ for a linearized variant of the problem with local observability.
  arXiv  Detail & Related papers  (2020-06-17T05:48:33Z)
• Latent Bandits Revisited [55.88616813182679]
  A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. We propose general algorithms for this setting, based on both upper confidence bounds (UCBs) and Thompson sampling. We provide a unified theoretical analysis of our algorithms, which have lower regret than classic bandit policies when the number of latent states is smaller than actions.
  arXiv  Detail & Related papers  (2020-06-15T19:24:02Z)
• MOTS: Minimax Optimal Thompson Sampling [89.2370817955411]
  It has remained an open problem whether Thompson sampling can match the minimax lower bound $Omega(sqrtKT)$ for $K$-armed bandit problems. We propose a variant of Thompson sampling called MOTS that adaptively clips the sampling instance of the chosen arm at each time step. We prove that this simple variant of Thompson sampling achieves the minimax optimal regret bound $O(sqrtKT)$ for finite time horizon $T$, as well as the optimal regret bound for Gaussian rewards when $T$ approaches infinity.
  arXiv  Detail & Related papers  (2020-03-03T21:24:39Z)
• On Thompson Sampling with Langevin Algorithms [106.78254564840844]
  Thompson sampling for multi-armed bandit problems enjoys favorable performance in both theory and practice. It suffers from a significant limitation computationally, arising from the need for samples from posterior distributions at every iteration. We propose two Markov Chain Monte Carlo (MCMC) methods tailored to Thompson sampling to address this issue.
  arXiv  Detail & Related papers  (2020-02-23T22:35:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.