{"total":45,"rows":[{"id":"2103.07501","title":"Beyond $\\log^2(T)$ Regret for Decentralized Bandits in Matching Markets","created":"2021-03-12","cited_by_count":30,"area":null},{"id":"2102.08462","title":"Multi-Agent Multi-Armed Bandits with Limited Communication","created":"2021-02-10","cited_by_count":29,"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":"2109.05700","title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","created":"2021-09-13","cited_by_count":20,"area":null},{"id":"2105.01798","title":"Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence","created":"2021-05-04","cited_by_count":18,"area":null},{"id":"2110.14622","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","cited_by_count":18,"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":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2208.09215","title":"Almost Cost-Free Communication in Federated Best Arm Identification","created":"2022-08-19","cited_by_count":11,"area":null},{"id":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2210.07780","title":"Federated Best Arm Identification with Heterogeneous Clients","created":"2022-10-14","cited_by_count":8,"area":null},{"id":"2211.02212","title":"Distributed Linear Bandits under Communication Constraints","created":"2022-11-04","cited_by_count":8,"area":null},{"id":"2302.07446","title":"On-Demand Communication for Asynchronous Multi-Agent Bandits","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2207.07948","title":"Collaborative Learning in Kernel-based Bandits for Distributed Users","created":"2022-07-16","cited_by_count":6,"area":null},{"id":"2207.08015","title":"Parallel Best Arm Identification in Heterogeneous Environments","created":"2022-07-16","cited_by_count":6,"area":null},{"id":"2310.11015","title":"Pure Exploration in Asynchronous Federated Bandits","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2106.04207","title":"Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2208.09029","title":"Communication-Efficient Collaborative Best Arm Identification","created":"2022-08-18","cited_by_count":5,"area":null},{"id":"2208.11530","title":"Collaborative Algorithms for Online Personalized Mean Estimation","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2203.10124","title":"Approximate Function Evaluation via Multi-Armed Bandits","created":"2022-03-18","cited_by_count":4,"area":null},{"id":"2305.18784","title":"Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2301.11442","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2308.04314","title":"Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2502.01425","title":"The Batch Complexity of Bandit Pure Exploration","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2212.06279","title":"Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2211.03985","title":"Adaptive Data Depth via Multi-Armed Bandits","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2303.17043","title":"Federated Learning for Heterogeneous Bandits with Unobserved Contexts","created":"2023-03-29","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":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2411.07094","title":"Differentially-Private Collaborative Online Personalized Mean Estimation","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2501.03132","title":"Communication Bounds for the Distributed Experts Problem","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2211.11524","title":"Conversion-Based Dynamic-Creative-Optimization in Native Advertising","created":"2022-11-13","cited_by_count":0,"area":null},{"id":"2312.09674","title":"Optimal Regret Bounds for Collaborative Learning in Bandits","created":"2023-12-15","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":"2505.10147","title":"Near Optimal Best Arm Identification for Clustered Bandits","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.10313","title":"Collaborative Min-Max Regret in Grouped Multi-Armed Bandits","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.15943","title":"On the optimal regret of collaborative personalized linear bandits","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2601.00615","title":"Integrating Multi-Armed Bandit, Active Learning, and Distributed Computing for Scalable Optimization","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2602.16183","title":"Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedback","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.21180","title":"ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2608.22120","title":"The Price of Decentralization in Top-$K$ Arm Identification","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}