{"total":158,"rows":[{"id":"2110.07788","title":"Gaussian Process Bandit Optimization with Few Batches","created":"2021-10-15","cited_by_count":57,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2107.02371","title":"Weighted Gaussian Process Bandits for Non-stationary Environments","created":"2021-07-06","cited_by_count":30,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2102.08314","title":"Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients","created":"2021-02-16","cited_by_count":20,"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":"2302.01511","title":"Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2311.03760","title":"Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds","created":"2023-11-07","cited_by_count":16,"area":null},{"id":"2110.12231","title":"Learning curves for Gaussian process regression with power-law priors and targets","created":"2021-10-23","cited_by_count":15,"area":null},{"id":"2203.07875","title":"Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization","created":"2022-03-15","cited_by_count":15,"area":null},{"id":"2206.04835","title":"Communication Efficient Distributed Learning for Kernelized Contextual Bandits","created":"2022-06-10","cited_by_count":15,"area":null},{"id":"2505.14756","title":"LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization","created":"2025-05-20","cited_by_count":14,"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":"2201.12909","title":"Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times","created":"2022-01-30","cited_by_count":13,"area":null},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","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":"2102.05793","title":"Lenient Regret and Good-Action Identification in Gaussian Process Bandits","created":"2021-02-11","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","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":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","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":"2209.10715","title":"Batch Bayesian optimisation via density-ratio estimation with guarantees","created":"2022-09-22","cited_by_count":9,"area":null},{"id":"2306.07092","title":"Tuning Legged Locomotion Controllers via Safe Bayesian Optimization","created":"2023-06-12","cited_by_count":9,"area":null},{"id":"2406.01163","title":"When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL","created":"2024-06-03","cited_by_count":9,"area":"deeprl"},{"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":"2401.17037","title":"Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration","created":"2024-01-30","cited_by_count":8,"area":null},{"id":"2402.06562","title":"Safe Guaranteed Exploration for Non-linear Systems","created":"2024-02-09","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":"2107.02377","title":"A Short Note on the Relationship of Information Gain and Eluder Dimension","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2410.10384","title":"Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal","created":"2024-10-14","cited_by_count":7,"area":null},{"id":"2205.04901","title":"Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization","created":"2022-05-10","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":"2210.10962","title":"Optimization on Manifolds via Graph Gaussian Processes","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2302.04376","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-08","cited_by_count":6,"area":null},{"id":"2305.03824","title":"No-Regret Constrained Bayesian Optimization of Noisy and Expensive Hybrid Models using Differentiable Quantile Function Approximations","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2409.06142","title":"Variational Search Distributions","created":"2024-09-10","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":"2502.06645","title":"Koopman-Equivariant Gaussian Processes","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2503.07127","title":"Performance-driven Constrained Optimal Auto-Tuner for MPC","created":"2025-03-10","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":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2201.00655","title":"Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression","created":"2021-12-31","cited_by_count":5,"area":null},{"id":"2202.00602","title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","created":"2022-02-01","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":"2410.10452","title":"Principled Bayesian Optimisation in Collaboration with Human Experts","created":"2024-10-14","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":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2510.03893","title":"BONSAI: Structure-exploiting robust Bayesian optimization for networked black-box systems under uncertainty","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2312.01386","title":"On the Suboptimality of GP-UCB under Polynomial Effective Optimism","created":"2023-12-03","cited_by_count":4,"area":null},{"id":"2403.04764","title":"TS-RSR: A provably efficient approach for batch Bayesian Optimization","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2409.00979","title":"Regret Analysis for Randomized Gaussian Process Upper Confidence Bound","created":"2024-09-02","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":"2410.24071","title":"Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs","created":"2024-10-31","cited_by_count":4,"area":"deeprl"},{"id":"2501.09262","title":"On the convergence rate of noisy Bayesian Optimization with Expected Improvement","created":"2025-01-16","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":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2510.20725","title":"No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes","created":"2025-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2511.03606","title":"Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity","created":"2025-11-05","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":"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":"2304.06104","title":"Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2308.08291","title":"Robust Bayesian Satisficing","created":"2023-08-16","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":"2502.02121","title":"BILBO: BILevel Bayesian Optimization","created":"2025-02-04","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":"2503.20341","title":"Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context","created":"2025-03-26","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":"2603.09276","title":"On Regret Bounds of Thompson Sampling for Bayesian Optimization","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.12627","title":"Batched Kernelized Bandits: Refinements and Extensions","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2110.02248","title":"Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2111.14778","title":"Contextual Combinatorial Multi-output GP Bandits with Group Constraints","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2208.02704","title":"Bayesian Optimization with Informative Covariance","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2301.12412","title":"Contextual Causal Bayesian Optimisation","created":"2023-01-29","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":"2312.12676","title":"Bayesian Analysis of Combinatorial Gaussian Process Bandits","created":"2023-12-20","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":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2407.00567","title":"A Contextual Combinatorial Bandit Approach to Negotiation","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2408.12307","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","created":"2024-08-22","cited_by_count":2,"area":"offlinerl"},{"id":"2502.01226","title":"Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling","created":"2025-02-03","cited_by_count":2,"area":null}],"next_cursor":"100"}