{"total":51,"rows":[{"id":"2103.05324","title":"A Simple Approach for Non-stationary Linear Bandits","created":"2021-03-09","cited_by_count":54,"area":null},{"id":"2107.02237","title":"Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination","created":"2021-07-05","cited_by_count":53,"area":null},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52,"area":null},{"id":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44,"area":null},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40,"area":null},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28,"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":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19,"area":null},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11,"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":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2211.09100","title":"Global Optimization with Parametric Function Approximation","created":"2022-11-16","cited_by_count":7,"area":null},{"id":"2206.00099","title":"Provably and Practically Efficient Neural Contextual Bandits","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2206.05404","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","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":"2406.10131","title":"Linear Contextual Bandits with Hybrid Payoff: Revisited","created":"2024-06-14","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":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"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":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","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":"2503.12020","title":"Variance-Dependent Regret Lower Bounds for Contextual Bandits","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2311.00973","title":"Federated Linear Bandits with Finite Adversarial Actions","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"area":null},{"id":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2309.13896","title":"Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2406.17184","title":"Minimax Optimality in Contextual Dynamic Pricing with General Valuation Models","created":"2024-06-24","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":"2102.07987","title":"The Elliptical Potential Lemma for General Distributions with an Application to Linear Thompson Sampling","created":"2021-02-16","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":"2210.10278","title":"A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2311.01695","title":"Communication-Efficient Federated Non-Linear Bandit Optimization","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.13390","title":"Experimental Design for Semiparametric Bandits","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.30976","title":"Batched Stochastic Linear Bandits with 1-Bit Communication Constraints","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2202.08302","title":"Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2209.03224","title":"Dual Instrumental Method for Confounded Kernelized Bandits","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2503.00929","title":"Parameter-Adaptive Dynamic Pricing","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2604.03969","title":"Nearly Optimal Best Arm Identification for Semiparametric Bandits","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2606.20022","title":"Set Membership Estimation for Stochastic Linear Contextual Bandits","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.14319","title":"Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.15170","title":"Nearly Minimax-Optimal Regret for Linear Contextual Bandits with Arbitrary Adaptive Action Sets","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}