mlsanityData to 7 Oct 2026

Meta-Thompson Sampling

arXiv 2102.06129 ↗First posted 11 Feb 2021cs.LG stat.MLcited by 62

Not on the map. Why?

Abstract (arXiv)

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several efficient implementations of MetaTS and analyze it in Gaussian bandits. Our analysis shows the benefit of meta-learning and is of a broader interest, because we derive a novel prior-dependent Bayes regret bound for Thompson sampling. Our theory is complemented by empirical evaluation, which shows that MetaTS quickly adapts to the unknown prior.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 16 of its 36 references that are in the map. First posted on arXiv 11 Feb 2021.

Builds on

16 of 36 references.

References · 16

  1. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  2. 2017A Tutorial on Thompson Samplingcited by 420
  3. 2013Learning to Optimize Via Posterior Samplingcited by 253
  4. 2014Online Clustering of Banditscited by 99
  5. 2019Meta-learning of Sequential Strategiescited by 68
  6. 2014Algorithms for multi-armed bandit problemscited by 63
  7. 2019Information-Theoretic Confidence Bounds for Reinforcement Learningcited by 51
  8. 2017Multi-Task Learning for Contextual Banditscited by 47
  9. 2020Meta-learning with Stochastic Linear Banditscited by 45
  10. 2020Latent Bandits Revisitedcited by 43
  11. 2019Meta Dynamic Pricing: Transfer Learning Across Experimentscited by 41
  12. 2013Sequential Transfer in Multi-armed Bandit with Finite Set of Modelscited by 38
4 more
  1. 2020Policy Gradient Optimization of Thompson Sampling Policiescited by 8
  2. 2019Empirical Bayes Regret Minimizationcited by 6
  3. 2020Differentiable Linear Bandit Algorithmcited by 5
  4. 2020Meta-Learning Bandit Policies by Gradient Ascentcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 19; 2023: 12; 2024: 9; 2025: 8; 2026: 6.

62 papers.

Sort:

By area:

  1. 2021Bayesian decision-making under misspecified priors with applications to meta-learningcited by 43
  2. 2021Hierarchical Bayesian Banditscited by 33
  3. 2021No Regrets for Learning the Prior in Banditscited by 29
  4. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  5. 2022Multi-task Representation Learning with Stochastic Linear Banditscited by 20
  6. 2022Deep Hierarchy in Banditscited by 18
  7. 2021Metalearning Linear Bandits by Prior Updatecited by 15
  8. 2022Safe Exploration for Efficient Policy Evaluation and Comparisoncited by 15
  9. 2022Mixed-Effect Thompson Samplingcited by 14
  10. 2023Leveraging Demonstrations to Improve Online Learning: Quality Matterscited by 13
  11. 2021Multitask Learning and Bandits via Robust Statisticscited by 11
  12. 2022Meta-Learning for Simple Regret Minimizationcited by 10
38 more
  1. 2022Towards Scalable and Robust Structured Bandits: A Meta-Learning Frameworkcited by 10
  2. 2022Hierarchical Conversational Preference Elicitation with Bandit Feedbackcited by 10
  3. 2022Multi-Task Off-Policy Learning from Bandit Feedbackcited by 9
  4. 2022Synthetically Controlled Banditscited by 8
  5. 2022Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Armscited by 8
  6. 2023Meta-Learning Adversarial Bandit Algorithmscited by 8
  7. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
  8. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  9. 2023Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneitycited by 7
  10. 2024Meta Clustering of Neural Banditscited by 7
  11. 2022Meta Representation Learning with Contextual Linear Banditscited by 6
  12. 2024Random Latent Exploration for Deep Reinforcement Learningcited by 6
  13. 2022Meta-Learning Adversarial Banditscited by 5
  14. 2022On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structurecited by 5
  15. 2023Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learningcited by 5
  16. 2024Diffusion Models Meet Contextual Banditscited by 5
  17. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  18. 2026Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directionscited by 5
  19. 2021Safe Data Collection for Offline and Online Policy Learningcited by 4
  20. 2022Multi-Environment Meta-Learning in Stochastic Linear Banditscited by 4
  21. 2022Robust Contextual Linear Banditscited by 4
  22. 2024Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Banditscited by 4
  23. 2024Meta Learning in Bandits within Shared Affine Subspacescited by 4
  24. 2022Tractable Optimality in Episodic Latent MABscited by 3
  25. 2023Only Pay for What Is Uncertain: Variance-Adaptive Thompson Samplingcited by 3
  26. 2023Context-lumpable stochastic banditscited by 3
  27. 2025Contextual Online Pricing with (Biased) Offline Datacited by 3
  28. 2022Online Meta-Learning in Adversarial Multi-Armed Banditscited by 2
  29. 2024Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysiscited by 2
  30. 2024Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysiscited by 1
  31. 2024Multi-Task Dynamic Pricing in Credit Market with Contextual Informationcited by 1
  32. 2025Adaptive Prior Selection in Gaussian Process Bandits with Thompson Samplingcited by 1
  33. 2025A Classification View on Meta Learning Banditscited by 1
  34. 2021Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodescited by 0
  35. 2022Online Bayesian Meta-Learning for Cognitive Tracking Radarcited by 0
  36. 2022Learning to Sell a Focal-ancillary Combinationcited by 0
  37. 2023Sequential Best-Arm Identification with Application to Brain-Computer Interfacecited by 0
  38. 2023Finite-Time Logarithmic Bayes Regret Upper Boundscited by 0

50 most cited of 62 All 62 (JSON)