{"total":58,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2106.03365","title":"Generalized Linear Bandits with Local Differential Privacy","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"area":null},{"id":"2202.05567","title":"Shuffle Private Linear Contextual Bandits","created":"2022-02-11","cited_by_count":27,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22,"area":null},{"id":"2110.09722","title":"Lipschitz Bandits with Batched Feedback","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2211.05632","title":"Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms","created":"2022-11-08","cited_by_count":19,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2112.06008","title":"Privacy Amplification via Shuffling for Linear Contextual Bandits","created":"2021-12-11","cited_by_count":17,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2308.08497","title":"HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2110.08057","title":"Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits","created":"2021-10-15","cited_by_count":9,"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":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2202.07079","title":"Synthetically Controlled Bandits","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2408.00465","title":"Infrequent Resolving Algorithm for Online Linear Programming","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2111.02314","title":"Online Learning of Energy Consumption for Navigation of Electric Vehicles","created":"2021-11-03","cited_by_count":7,"area":null},{"id":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6,"area":null},{"id":"2410.02068","title":"Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2502.17292","title":"Joint Value Estimation and Bidding in Repeated First-Price Auctions","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2302.14015","title":"CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2207.05250","title":"Efficient Real-world Testing of Causal Decision Making via Bayesian Experimental Design for Contextual Optimisation","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2311.00973","title":"Federated Linear Bandits with Finite Adversarial Actions","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2311.01327","title":"High-dimensional Linear Bandits with Knapsacks","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2311.13180","title":"Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks","created":"2023-11-22","cited_by_count":3,"area":null},{"id":"2402.17732","title":"Batched Nonparametric Contextual Bandits","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2510.23992","title":"Optimal Arm Elimination Algorithms for Combinatorial Bandits","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2206.02092","title":"Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization","created":"2022-06-05","cited_by_count":2,"area":null},{"id":"2301.12535","title":"Concurrent Shuffle Differential Privacy Under Continual Observation","created":"2023-01-29","cited_by_count":2,"area":null},{"id":"2405.05733","title":"Batched Stochastic Bandit for Nondegenerate Functions","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2507.08438","title":"Optimal and Practical Batched Linear Bandit Algorithm","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2606.00984","title":"Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2111.02071","title":"The Impact of Batch Learning in Stochastic Bandits","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2505.10498","title":"Batched Nonparametric Bandits via k-Nearest Neighbor UCB","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.13742","title":"Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2103.09927","title":"Encrypted Linear Contextual Bandit","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2206.04180","title":"Learning in Distributed Contextual Linear Bandits Without Sharing the Context","created":"2022-06-08","cited_by_count":0,"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":"2501.17370","title":"Breaking the $\\log(1/\\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2509.04194","title":"Stochastic Matching Bandits with Rare Optimization Updates","created":"2025-09-04","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":"2511.03708","title":"The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","cited_by_count":0,"area":null}],"next_cursor":null}