mlsanityData to 7 Oct 2026

Neural Thompson Sampling

arXiv 2010.00827 ↗First posted 2 Oct 2020cs.LG stat.MLcited by 127

Not on the map. Why?

Abstract (arXiv)

Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achieve a cumulative regret of O(T1/2), which matches the regret of other contextual bandit algorithms in terms of total round number T. Experimental comparisons with other benchmark bandit algorithms on various data sets corroborate our theory.

Key facts. Cited by 127 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 22; 2023: 19; 2024: 20; 2025: 28; 2026: 22.

127 papers.

Sort:

By area:

  1. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  2. 2021Optimal Order Simple Regret for Gaussian Process Banditscited by 52
  3. 2024Efficient Exploration for LLMscited by 44
  4. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  5. 2021Neural Contextual Bandits without Regretcited by 40
  6. 2024Prompt Optimization with Human Feedbackcited by 35
  7. 2022Contextual Bandits with Large Action Spaces: Made Practicalcited by 32
  8. 2023Approximate Thompson Sampling via Epistemic Neural Networkscited by 31
  9. 2022A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learningcited by 30
  10. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  11. 2023The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learningcited by 27
  12. 2022Sample-Then-Optimize Batch Neural Thompson Samplingcited by 25
38 more
  1. 2021Batched Neural Banditscited by 22
  2. 2021Neural Active Learning with Performance Guaranteescited by 22
  3. 2022Langevin Monte Carlo for Contextual Banditscited by 22
  4. 2021Uniform Generalization Bounds for Overparameterized Neural Networkscited by 21
  5. 2023Graph Neural Banditscited by 20
  6. 2022Learning Neural Contextual Bandits Through Perturbed Rewardscited by 17
  7. 2022Federated Neural Banditscited by 17
  8. 2022An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledgecited by 17
  9. 2023Combinatorial Neural Banditscited by 16
  10. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 16
  11. 2021Efficient Online Bayesian Inference for Neural Banditscited by 15
  12. 2021Online Limited Memory Neural-Linear Bandits with Likelihood Matchingcited by 14
  13. 2021Deep Exploration for Recommendation Systemscited by 14
  14. 2024PageRank Bandits for Link Predictioncited by 14
  15. 2021Pure Exploration in Kernel and Neural Banditscited by 13
  16. 2021Open Problem: Tight Online Confidence Intervals for RKHS Elementscited by 13
  17. 2023Scalable Neural Contextual Bandit for Recommender Systemscited by 12
  18. 2023Quantum Bayesian Optimizationcited by 12
  19. 2022Improved Algorithms for Neural Active Learningcited by 11
  20. 2021Quantifying Epistemic Uncertainty in Deep Learningcited by 10
  21. 2022Graph Neural Network Banditscited by 10
  22. 2023Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networkscited by 10
  23. 2023Neural Contextual Bandits for Personalized Recommendationcited by 10
  24. 2025ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignmentcited by 9
  25. 2022Neural Bandit with Arm Group Graphcited by 8
  26. 2022Neural Collaborative Filtering Bandits via Meta Learningcited by 7
  27. 2022Global Optimization with Parametric Function Approximationcited by 7
  28. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  29. 2024Neural Dueling Bandits: Preference-Based Optimization with Human Feedbackcited by 7
  30. 2024Meta Clustering of Neural Banditscited by 7
  31. 2022Provably and Practically Efficient Neural Contextual Banditscited by 6
  32. 2023On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspectivecited by 6
  33. 2025T-POP: Test-Time Personalization with Online Preference Feedbackcited by 6
  34. 2023VITS : Variational Inference Thompson Sampling for contextual banditscited by 5
  35. 2024Online Personalizing White-box LLMs Generation with Neural Banditscited by 5
  36. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  37. 2025Neural Logistic Banditscited by 5
  38. 2021Adversarial Gradient Driven Exploration for Deep Click-Through Rate Predictioncited by 4

50 most cited of 127 All 127 (JSON)