mlsanityData to 7 Oct 2026

Batched Neural Bandits

arXiv 2102.13028 ↗First posted 25 Feb 2021cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

In many sequential decision-making problems, the individuals are split into several batches and the decision-maker is only allowed to change her policy at the end of batches. These batch problems have a large number of applications, ranging from clinical trials to crowdsourcing. Motivated by this, we study the stochastic contextual bandit problem for general reward distributions under the batched setting. We propose the BatchNeuralUCB algorithm which combines neural networks with optimism to address the exploration-exploitation tradeoff while keeping the total number of batches limited. We study BatchNeuralUCB under both fixed and adaptive batch size settings and prove that it achieves the same regret as the fully sequential version while reducing the number of policy updates considerably. We confirm our theoretical results via simulations on both synthetic and real-world datasets.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

20 of 43 references.

References · 20

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  2. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  3. 2019Introduction to Multi-Armed Banditscited by 475
  4. 2019Batch Policy Learning under Constraintscited by 242
  5. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  6. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  7. 2019Neural Tangents: Fast and Easy Infinite Neural Networks in Pythoncited by 149
  8. 2020Neural Thompson Samplingcited by 127
  9. 2019Batched Multi-armed Bandits Problemcited by 97
  10. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  11. 2020Sequential Batch Learning in Finite-Action Linear Contextual Banditscited by 63
  12. 2013Online Learning with Switching Costs and Other Adaptive Adversariescited by 60
8 more
  1. 2020Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Designcited by 51
  2. 2019A Survey on Practical Applications of Multi-Armed and Contextual Banditscited by 44
  3. 2013Bandits with Switching Costs: T^{2/3} Regretcited by 38
  4. 2020Double Explore-then-Commit: Asymptotic Optimality and Beyondcited by 24
  5. 2019Adaptivity in Adaptive Submodularitycited by 22
  6. 2019Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transitioncited by 17
  7. 2019Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matchingcited by 16
  8. 2019Phase Transitions in Bandits with Switching Constraintscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 4; 2024: 3; 2025: 2; 2026: 1.

22 papers.

Sort:

By area:

  1. 2021Neural Contextual Bandits without Regretcited by 40
  2. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  3. 2022Sample-Then-Optimize Batch Neural Thompson Samplingcited by 25
  4. 2022Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimalitycited by 24
  5. 2021Uniform Generalization Bounds for Overparameterized Neural Networkscited by 21
  6. 2022Federated Neural Banditscited by 17
  7. 2022An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledgecited by 17
  8. 2022Graph Neural Network Banditscited by 10
  9. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  10. 2022Provably and Practically Efficient Neural Contextual Banditscited by 6
  11. 2023A General Framework for Sequential Decision-Making under Adaptivity Constraintscited by 6
  12. 2022Reward Imputation with Sketching for Contextual Batched Banditscited by 5
10 more
  1. 2021Parallelizing Contextual Banditscited by 4
  2. 2022Reward-Biased Maximum Likelihood Estimation for Neural Contextual Banditscited by 2
  3. 2022Two-Stage Neural Contextual Bandits for Personalised News Recommendationcited by 2
  4. 2024Stochastic Bandits with ReLU Neural Networkscited by 2
  5. 2025Online Clustering of Dueling Banditscited by 2
  6. 2023Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Samplingcited by 1
  7. 2024IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution Historycited by 1
  8. 2024Graph Neural Thompson Samplingcited by 1
  9. 2025Batched Nonparametric Bandits via k-Nearest Neighbor UCBcited by 1
  10. 2026Replicable Bandits with UCB based Explorationcited by 0