mlsanityData to 7 Oct 2026

An Analysis of Ensemble Sampling

arXiv 2203.01303 ↗First posted 2 Mar 2022cs.LG stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling is applied to the linear bandit problem. This represents the first rigorous regret analysis of ensemble sampling and is made possible by leveraging information-theoretic concepts and novel analytic techniques that may prove useful beyond the scope of this paper.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

25 of 52 references.

References · 25

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  2. 2017Deep Neural Networks as Gaussian Processescited by 617
  3. 2016Deep Exploration via Bootstrapped DQNcited by 518
  4. 2017A Tutorial on Thompson Samplingcited by 420
  5. 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
  6. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  7. 2014An Information-Theoretic Analysis of Thompson Samplingcited by 178
  8. 2017Deep Exploration via Randomized Value Functionscited by 155
  9. 2016Simple Bayesian Algorithms for Best Arm Identificationcited by 116
  10. 2015Online Learning with Feedback Graphs: Beyond Banditscited by 79
  11. 2017Ensemble Samplingcited by 62
  12. 2020Hypermodels for Explorationcited by 37
13 more
  1. 2014Efficient Learning in Large-Scale Combinatorial Semi-Banditscited by 36
  2. 2018Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Banditscited by 33
  3. 2019On the Performance of Thompson Sampling on Logistic Banditscited by 32
  4. 2019Perturbed-History Exploration in Stochastic Linear Banditscited by 28
  5. 2021From Predictions to Decisions: The Importance of Joint Predictive Distributionscited by 28
  6. 2020Targeting for long-term outcomescited by 23
  7. 2021The Neural Testbed: Evaluating Joint Predictionscited by 22
  8. 2014Thompson sampling with the online bootstrapcited by 19
  9. 2018Coordinated Exploration in Concurrent Reinforcement Learningcited by 17
  10. 2017Variational inference for the multi-armed contextual banditcited by 15
  11. 2021Deep Exploration for Recommendation Systemscited by 14
  12. 2019Scalable Thompson Sampling via Optimal Transportcited by 7
  13. 2021Anti-Concentrated Confidence Bonuses for Scalable Explorationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 5; 2025: 7; 2026: 4.

23 papers.

Sort:

By area:

  1. 2022Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Banditscited by 19
  2. 2022Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrappingcited by 19
  3. 2024Sample-Efficient Alignment for LLMscited by 16
  4. 2023Leveraging Demonstrations to Improve Online Learning: Quality Matterscited by 13
  5. 2023Scalable Neural Contextual Bandit for Recommender Systemscited by 12
  6. 2023Ensemble sampling for linear bandits: small ensembles sufficecited by 7
  7. 2025Adaptive Elicitation of Latent Information Using Natural Languagecited by 7
  8. 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgentcited by 6
  9. 2024Online Bandit Learning with Offline Preference Data for Improved RLHFcited by 6
  10. 2024Improved Regret of Linear Ensemble Samplingcited by 6
  11. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  12. 2025Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Storycited by 4
11 more
  1. 2023Multiplier Bootstrap-based Explorationcited by 3
  2. 2025Best Policy Learning from Trajectory Preference Feedbackcited by 3
  3. 2025Contextual Similarity Distillation: Ensemble Uncertainties with a Single Modelcited by 3
  4. 2025Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Banditscited by 2
  5. 2023Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Samplingcited by 1
  6. 2025Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspectivecited by 1
  7. 2026Sharp analysis of linear ensemble samplingcited by 1
  8. 2024Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Banditscited by 0
  9. 2026K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agentscited by 0
  10. 2026DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experimentscited by 0
  11. 2026Linear Ensemble Sampling with Smaller Ensemblescited by 0