{"total":54,"rows":[{"id":"2110.07788","title":"Gaussian Process Bandit Optimization with Few Batches","created":"2021-10-15","cited_by_count":57,"area":null},{"id":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","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":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","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":"2111.09885","title":"Rate-optimal Bayesian Simple Regret in Best Arm Identification","created":"2021-11-18","cited_by_count":11,"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":"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":"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":"2410.16052","title":"Near-Optimal Algorithm for Non-Stationary Kernelized Bandits","created":"2024-10-21","cited_by_count":8,"area":null},{"id":"2209.09655","title":"Lower Bounds on the Worst-Case Complexity of Efficient Global Optimization","created":"2022-09-20","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":"2310.11015","title":"Pure Exploration in Asynchronous Federated Bandits","created":"2023-10-17","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":"2306.04454","title":"Training-Free Neural Active Learning with Initialization-Robustness Guarantees","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2410.16972","title":"Sample-efficient Bayesian Optimisation Using Known Invariances","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2506.04775","title":"Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2507.09828","title":"Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization","created":"2025-07-13","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":"2202.10615","title":"On Average-Case Error Bounds for Kernel-Based Bayesian Quadrature","created":"2022-02-22","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":"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":"2401.05716","title":"Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization","created":"2024-01-11","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":"2410.15543","title":"Distributed Thompson sampling under constrained communication","created":"2024-10-21","cited_by_count":2,"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":"2406.10686","title":"Graph Neural Thompson Sampling","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"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":"2312.04719","title":"Distributed Optimization via Kernelized Multi-armed Bandits","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2402.03243","title":"PINN-BO: A Black-box Optimization Algorithm using Physics-Informed Neural Networks","created":"2024-02-05","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":"2505.24692","title":"Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms","created":"2025-05-30","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":"2605.31050","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},{"id":"2606.00956","title":"Towards Regret Guarantees for One-Step Lookahead Bayesian Optimization","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2610.16187","title":"Exploration strategies for Gaussian process bandit optimization with inference regret guarantees","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18434","title":"Principled Design of Expected Improvement for Continuous Simulation Optimization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}