{"total":60,"rows":[{"id":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2102.09626","title":"A Simple Unified Framework for High Dimensional Bandit Problems","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"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":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","cited_by_count":17,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2211.05964","title":"Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits","created":"2022-11-11","cited_by_count":16,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2402.11156","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","created":"2024-02-17","cited_by_count":10,"area":null},{"id":"2211.02212","title":"Distributed Linear Bandits under Communication Constraints","created":"2022-11-04","cited_by_count":8,"area":null},{"id":"2309.08634","title":"Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing","created":"2023-09-14","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":"2310.18465","title":"Nearly Minimax Optimal Submodular Maximization with Bandit Feedback","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","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":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"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":"2306.11017","title":"High-dimensional Contextual Bandit Problem without Sparsity","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2411.02383","title":"Linear Causal Bandits: Unknown Graph and Soft Interventions","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2503.07555","title":"Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference","created":"2025-03-10","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":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2202.13448","title":"Federated Online Sparse Decision Making","created":"2022-02-27","cited_by_count":3,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2307.04055","title":"Contextual Dynamic Pricing with Strategic Buyers","created":"2023-07-08","cited_by_count":3,"area":null},{"id":"2310.00532","title":"Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference","created":"2023-10-01","cited_by_count":3,"area":null},{"id":"2310.15286","title":"A Doubly Robust Approach to Sparse Reinforcement Learning","created":"2023-10-23","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":"2401.06173","title":"Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","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":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2406.01192","title":"Sparsity-Agnostic Linear Bandits with Adaptive Adversaries","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2510.21119","title":"Leveraging semantic similarity for experimentation with AI-generated treatments","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2209.08403","title":"Advertising Media and Target Audience Optimization via High-dimensional Bandits","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2302.00814","title":"Stochastic Contextual Bandits with Long Horizon Rewards","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2311.00481","title":"Fixed-Budget Best-Arm Identification in Sparse Linear Bandits","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2405.14038","title":"FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2501.10722","title":"A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits","created":"2025-01-18","cited_by_count":1,"area":null},{"id":"2505.14102","title":"High-dimensional Nonparametric Contextual Bandit Problem","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2506.03324","title":"Optimization of Epsilon-Greedy Exploration","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.19752","title":"On the necessity of adaptive regularisation:Optimal anytime online learning on $\\boldsymbol{\\ell_p}$-balls","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2510.24234","title":"Sparse Optimistic Information Directed Sampling","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2402.03737","title":"Differentially Private High Dimensional Bandits","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2410.20041","title":"Sparse Linear Bandits with Blocking Constraints","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2502.07397","title":"Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2510.08435","title":"Navigating Sparsities in High-Dimensional Linear Contextual Bandits","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.26000","title":"Infrequent Exploration in Linear Bandits","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2605.10151","title":"Learning to Sparsify Stochastic Linear Bandits","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27794","title":"Learning to target with network interference","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}