{"total":39,"rows":[{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2306.07745","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","created":"2023-06-13","cited_by_count":20,"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":"2506.01393","title":"Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2502.19006","title":"Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2311.02268","title":"LLMs-augmented Contextual Bandit","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","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":"2310.00137","title":"On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2304.13830","title":"Adaptation to Misspecified Kernel Regularity in Kernelised Bandits","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2306.04454","title":"Training-Free Neural Active Learning with Initialization-Robustness Guarantees","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2305.19922","title":"Representation-Driven Reinforcement Learning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2410.16972","title":"Sample-efficient Bayesian Optimisation Using Known Invariances","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2602.17940","title":"Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere","created":"2026-02-20","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":"2303.01682","title":"Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","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":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"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":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2503.10836","title":"Exploiting Concavity Information in Gaussian Process Contextual Bandit Optimization","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2402.11427","title":"OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2502.02290","title":"FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detection","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.12086","title":"Neural Contextual Bandits Under Delayed Feedback Constraints","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2601.06913","title":"Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2606.01457","title":"Transferring Information Across Interventions in Causal Bayesian Optimization","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":null}