{"total":21,"rows":[{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2310.02905","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","created":"2023-10-02","cited_by_count":30,"area":null},{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2205.14309","title":"Federated Neural Bandits","created":"2022-05-28","cited_by_count":17,"area":null},{"id":"2205.14775","title":"An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge","created":"2022-05-29","cited_by_count":17,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2206.00099","title":"Provably and Practically Efficient Neural Contextual Bandits","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2203.04192","title":"Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2206.14648","title":"Two-Stage Neural Contextual Bandits for Personalised News Recommendation","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2405.07331","title":"Stochastic Bandits with ReLU Neural Networks","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2310.07786","title":"Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2406.10686","title":"Graph Neural Thompson Sampling","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2505.10498","title":"Batched Nonparametric Bandits via k-Nearest Neighbor UCB","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2604.20024","title":"Replicable Bandits with UCB based Exploration","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}