Overview

Thompson sampling maintains a probability model of uncertain rewards, samples a plausible model, and chooses the action that looks best under that sample. It is studied in multi-armed and contextual bandits, linear and combinatorial settings, and Bayesian optimization with Gaussian processes; methods range from conjugate posteriors to nonparametric models and approximate sampling algorithms. Regret analyses give guarantees for many settings, while practical work adapts the method to changing rewards, structured actions, privacy, and limited computation. Open tensions include sensitivity to priors and model misspecification, the cost of accurate posterior sampling, and how to retain strong guarantees under non-stationarity or complex feedback.

Latest papers

CardsList

57 papers5 papers in the last four weeks, down 55% on the four weeks before. 0.0% of all new papers.

  1. Terrain-Aware Thompson Sampling for Multi-Drone Search and Rescue

    Nov 10, 2026Riana Gagnon Souleiman, Giovanni BeltrameSearch-and-Rescue RoboticsUncertainty-Aware Exploration

  2. Thompson Sampling using Prior-fitted Diffusion Transformers

    Nov 10, 2026Sihwa Park, Jingsen Zhu, Vinamr Jain +2Thompson SamplingBlack-Box Optimization

  3. Meta-Frieren: Beyond Single Level Online Learning

    Nov 4, 2026Vahan Arsenyan, Arnak DalalyanMulti-Armed BanditsThompson Sampling

  4. Exploratory creative pre-ranking: Hierarchical empirical-Bayes Thompson sampling for real-time creative optimization

    Oct 26, 2026Jiale Han, Ajith Moparthi, Dan Xie +1Learning to RankThompson Sampling

  5. Amortized Thompson Sampling and Efficient Information-Directed Sampling for Simulator-Based Design

    Oct 23, 2026Michal Kobiela, Michael U. GutmannThompson SamplingBayesian Experimental Design

  6. Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search

    Oct 16, 2026Quynh Trinh, Trung Nguyen, Nam Nguyen +1Risk-Sensitive PlanningMonte Carlo Tree Search

  7. The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret

    Oct 15, 2026Mohammad Pedramfar, Siamak RavanbakhshPosterior SamplingThompson Sampling

  8. High-Probability Regret Bounds for Feel-Good Thompson Sampling

    Oct 14, 2026Xuheng Li, Qingyue Zhao, Quanquan GuThompson SamplingContextual Bandits

  9. Expected Sample Complexity in Multi-Armed Bandits

    Oct 7, 2026Nadav Sukenik, Nadav MerlisMulti-Armed BanditsRegret Minimization

  10. Ranking Bandits for Carousel Interfaces with Observable Browsing Depth

    Oct 4, 2026Takuma Yasuda, Atsuyoshi Nakamura, Dai Hai NguyenThompson SamplingMulti-Armed Bandits

  11. Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets

    Sep 30, 2026Priyanath Maji, Spandan Ghose ChowdhuryThompson SamplingAI Agent Evaluation

  12. A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets

    Sep 26, 2026Arda Güçlü, Subhonmesh Bose, John R. BirgeMulti-Armed BanditsUCB Algorithms

  13. Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits

    Sep 23, 2026Prakhar Singhvi, Yi Zou, Abhishek BhattacharjeeThompson SamplingMulti-Armed Bandits

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

    Sep 2, 2026Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya +1Thompson SamplingMulti-Armed Bandits

  15. On-Policy and Off-Policy Learning for Large Action Spaces

    Jul 30, 2026Imad AoualiThompson SamplingMulti-Armed Bandits

  16. Periodic Bootstrap Thompson Sampling For Periodically Non-Stationary Bandit Problems

    Jul 18, 2026Boning ShaoThompson SamplingNon-Stationary Bandits

  17. Information-Directed Sampling for Causal Bandits

    Jul 17, 2026Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa GhasemiThompson SamplingMulti-Armed Bandits

  18. Link Adaptation Using Joint-Thompson Sampling

    Jul 13, 2026Vignatha Vinjam, Manjunath Kolavennu, Myna Vajha +1Thompson SamplingMulti-Armed Bandits

  19. Randomized Exploration for Linear Bandits via Absolute Perturbations

    Jun 26, 2026Toshinori Kitamura, Shuai Liu, Csaba SzepesváriThompson SamplingMulti-Armed Bandits

  20. Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits

    Jun 22, 2026AmirHossein Naghdi, Ali BaheriThompson SamplingNon-Stationary Bandits

  21. AdaPrivate-TS: Private Thompson Sampling for Contextual Bandits with Privacy Amplification

    Jun 19, 2026Mohammadreza Riyazat, Eranga UkwattaThompson SamplingDifferential Privacy

  22. Bayesian Anytime Pareto Set Identification for Multi-Objective Multi-Armed Bandits

    Jun 17, 2026Lennert Saerens, Bram Silue, Eleni Litsa +2Thompson SamplingMulti-Armed Bandits