{"total":40,"rows":[{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48,"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":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","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":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2501.17513","title":"Sequential Learning of the Pareto Front for Multi-objective Bandits","created":"2025-01-29","cited_by_count":15,"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":"2306.05275","title":"Federated Linear Contextual Bandits with User-level Differential Privacy","created":"2023-06-08","cited_by_count":12,"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":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","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":"2303.09390","title":"On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2211.15129","title":"On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2405.10815","title":"A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization","created":"2024-05-17","cited_by_count":4,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2109.14703","title":"Sequential Estimation under Multiple Resources: a Bandit Point of View","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2312.12731","title":"Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","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":"2605.28290","title":"Adaptive Bandit Algorithms for Contextual Matching Markets","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2201.02169","title":"Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach","created":"2022-01-06","cited_by_count":0,"area":null},{"id":"2301.12571","title":"Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2402.03737","title":"Differentially Private High Dimensional Bandits","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2503.15962","title":"Information maximization for a broad variety of multi-armed bandit games","created":"2025-03-20","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":"2504.03926","title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2509.05864","title":"Beyond ATE: Multi-Criteria Design for A/B Testing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2603.12530","title":"Mixing Makes Markovian Contexts Cheap for Linear Bandits","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null}],"next_cursor":null}