{"total":309,"rows":[{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415,"area":null},{"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":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","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":"2105.02796","title":"Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression","created":"2021-05-06","cited_by_count":49,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38,"area":null},{"id":"2202.07549","title":"Robust Multi-Objective Bayesian Optimization Under Input Noise","created":"2022-02-15","cited_by_count":37,"area":null},{"id":"2301.12844","title":"Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?","created":"2023-01-30","cited_by_count":36,"area":null},{"id":"2110.14153","title":"Differentially Private Federated Bayesian Optimization with Distributed Exploration","created":"2021-10-27","cited_by_count":32,"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":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27,"area":null},{"id":"2403.19390","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","created":"2024-03-28","cited_by_count":27,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","cited_by_count":22,"area":null},{"id":"2205.14090","title":"Surrogate modeling for Bayesian optimization beyond a single Gaussian process","created":"2022-05-27","cited_by_count":22,"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":"2105.06126","title":"Value-at-Risk Optimization with Gaussian Processes","created":"2021-05-13","cited_by_count":20,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","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":"2102.06296","title":"No-Regret Algorithms for Time-Varying Bayesian Optimization","created":"2021-02-11","cited_by_count":19,"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":"2109.02606","title":"Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications","created":"2021-09-06","cited_by_count":17,"area":null},{"id":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2111.03637","title":"Risk-averse Heteroscedastic Bayesian Optimization","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"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":"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":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2406.20062","title":"Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index","created":"2024-06-28","cited_by_count":16,"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":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","cited_by_count":14,"area":null},{"id":"2104.09582","title":"Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approach","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2203.07322","title":"Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation","created":"2022-03-14","cited_by_count":14,"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":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","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":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"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":"2310.15641","title":"Guaranteed Coverage Prediction Intervals with Gaussian Process Regression","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2312.10199","title":"Automatic nonlinear MPC approximation with closed-loop guarantees","created":"2023-12-15","cited_by_count":12,"area":null},{"id":"2102.12467","title":"No-Regret Algorithms for Private Gaussian Process Bandit Optimization","created":"2021-02-24","cited_by_count":11,"area":null},{"id":"2105.11802","title":"Bias-Robust Bayesian Optimization via Dueling Bandits","created":"2021-05-25","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":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2402.02629","title":"PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks","created":"2024-02-04","cited_by_count":11,"area":null},{"id":"2101.07825","title":"Safe and Efficient Model-free Adaptive Control via Bayesian Optimization","created":"2021-01-19","cited_by_count":10,"area":null},{"id":"2106.02979","title":"Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2109.11679","title":"Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment","created":"2021-09-22","cited_by_count":10,"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":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"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":"2211.14720","title":"Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2212.04914","title":"Information-Theoretic Safe Exploration with Gaussian Processes","created":"2022-12-09","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":"2401.02650","title":"Improving sample efficiency of high dimensional Bayesian optimization with MCMC","created":"2024-01-05","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":"2602.07904","title":"Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models","created":"2026-02-08","cited_by_count":9,"area":null},{"id":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2104.03743","title":"Residual Gaussian Process: A Tractable Nonparametric Bayesian Emulator for Multi-fidelity Simulations","created":"2021-04-08","cited_by_count":8,"area":null},{"id":"2206.06872","title":"On Provably Robust Meta-Bayesian Optimization","created":"2022-06-14","cited_by_count":8,"area":null},{"id":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2305.08169","title":"Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learning","created":"2023-05-14","cited_by_count":8,"area":null},{"id":"2311.01195","title":"Batch Bayesian Optimization for Replicable Experimental Design","created":"2023-11-02","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":"2405.18621","title":"Multi-Armed Bandits with Network Interference","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2409.01163","title":"PACSBO: Probably approximately correct safe Bayesian optimization","created":"2024-09-02","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":"2101.05328","title":"Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Control","created":"2021-01-13","cited_by_count":7,"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":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2203.13968","title":"Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization","created":"2022-03-26","cited_by_count":7,"area":null},{"id":"2208.10790","title":"Event-Triggered Time-Varying Bayesian Optimization","created":"2022-08-23","cited_by_count":7,"area":null},{"id":"2210.08087","title":"Movement Penalized Bayesian Optimization with Application to Wind Energy Systems","created":"2022-10-14","cited_by_count":7,"area":null},{"id":"2311.02715","title":"Exploiting Correlated Auxiliary Feedback in Parameterized Bandits","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2312.14470","title":"Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration","created":"2023-12-22","cited_by_count":7,"area":null},{"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}],"next_cursor":"100"}