{"total":57,"rows":[{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2110.09722","title":"Lipschitz Bandits with Batched Feedback","created":"2021-10-19","cited_by_count":21,"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":"2202.04005","title":"Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning","created":"2022-02-08","cited_by_count":18,"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":"2310.15351","title":"Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2502.06363","title":"Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2110.15458","title":"Open Problem: Tight Online Confidence Intervals for RKHS Elements","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"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":"2309.14298","title":"Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures","created":"2023-09-25","cited_by_count":12,"area":null},{"id":"2310.05373","title":"Quantum Bayesian Optimization","created":"2023-10-09","cited_by_count":12,"area":null},{"id":"2202.01850","title":"A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits","created":"2022-02-03","cited_by_count":11,"area":null},{"id":"2206.09341","title":"Bayesian Optimization under Stochastic Delayed Feedback","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2302.00392","title":"Delayed Feedback in Kernel Bandits","created":"2023-02-01","cited_by_count":10,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"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":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2403.12732","title":"Tighter Confidence Bounds for Sequential Kernel Regression","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2410.16052","title":"Near-Optimal Algorithm for Non-Stationary Kernelized Bandits","created":"2024-10-21","cited_by_count":8,"area":null},{"id":"2402.08406","title":"Transition Constrained Bayesian Optimization via Markov Decision Processes","created":"2024-02-13","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":"2207.07948","title":"Collaborative Learning in Kernel-based Bandits for Distributed Users","created":"2022-07-16","cited_by_count":6,"area":null},{"id":"2410.23498","title":"Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm","created":"2024-10-30","cited_by_count":6,"area":"deeprl"},{"id":"2411.03641","title":"Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2110.08449","title":"Adversarial Attacks on Gaussian Process Bandits","created":"2021-10-16","cited_by_count":5,"area":null},{"id":"2203.06297","title":"Instance-Dependent Regret Analysis of Kernelized Bandits","created":"2022-03-12","cited_by_count":5,"area":null},{"id":"2410.16692","title":"Lower Bounds for Time-Varying Kernelized Bandits","created":"2024-10-22","cited_by_count":5,"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":"2211.05430","title":"Regret Bounds for Noise-Free Cascaded Kernelized Bandits","created":"2022-11-10","cited_by_count":3,"area":null},{"id":"2301.12061","title":"(Private) Kernelized Bandits with Distributed Biased Feedback","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2501.07046","title":"Differentially Private Kernelized Contextual Bandits","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2502.16870","title":"Distributionally Robust Active Learning for Gaussian Process Regression","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2505.23673","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","created":"2025-05-29","cited_by_count":3,"area":"alignment"},{"id":"2603.12627","title":"Batched Kernelized Bandits: Refinements and Extensions","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2405.05733","title":"Batched Stochastic Bandit for Nondegenerate Functions","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2406.15250","title":"Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning","created":"2024-06-21","cited_by_count":2,"area":"deeprl"},{"id":"2512.05957","title":"Consequences of Kernel Regularity for Bandit Optimization","created":"2025-12-05","cited_by_count":2,"area":null},{"id":"2603.01470","title":"Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2211.01561","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2605.10299","title":"Nearly-Optimal Algorithm for Adversarial Kernelized Bandits","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2608.16492","title":"Improved Regret Analysis for Parallel Gaussian Process Bandit Optimization","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2305.11509","title":"From Random Search to Bandit Learning in Metric Measure Spaces","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2402.13182","title":"Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2410.14533","title":"The Traveling Bandit: A Framework for Bayesian Optimization with Movement Costs","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.06529","title":"Direct Regret Optimization in Bayesian Optimization","created":"2025-07-09","cited_by_count":0,"area":"offlinerl"},{"id":"2507.13639","title":"Differential Privacy in Kernelized Contextual Bandits via Random Projections","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2510.03798","title":"Batched Bandits with Heavy-Tailed Rewards","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2604.25025","title":"A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.05967","title":"Sharper Guarantees for Misspecified Kernelized Bandit Optimization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.26585","title":"Near-Optimal Regret in Adversarial Kernel Bandits","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.31050","title":"Trajectory-Aware Best-Arm Identification for Local Search Allocation in Bayesian Optimization and Beyond","created":"2026-05-29","cited_by_count":0,"area":null}],"next_cursor":null}