{"total":29,"rows":[{"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":"2111.01570","title":"Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits","created":"2021-11-02","cited_by_count":11,"area":null},{"id":"2306.05579","title":"Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards","created":"2023-06-08","cited_by_count":11,"area":null},{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11,"area":null},{"id":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2207.05827","title":"Differentially Private Linear Bandits with Partial Distributed Feedback","created":"2022-07-12","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":"2204.12620","title":"Rate-Constrained Remote Contextual Bandits","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2206.02834","title":"Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds","created":"2022-06-06","cited_by_count":5,"area":null},{"id":"2202.05182","title":"Remote Contextual Bandits","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2109.09427","title":"Asymptotic Optimality for Decentralised Bandits","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2312.14259","title":"Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2308.08046","title":"Regret Lower Bounds in Multi-agent Multi-armed Bandit","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2312.15549","title":"Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2401.10383","title":"Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2402.04417","title":"Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2411.12154","title":"Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2601.11924","title":"Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Bandits","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2201.01182","title":"Modelling Cournot Games as Multi-agent Multi-armed Bandits","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2404.04509","title":"Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2502.15338","title":"Learning with Limited Shared Information in Multi-agent Multi-armed Bandit","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2510.22811","title":"Distributed Multi-Agent Bandits Over Erd\\H{o}s-R\\'enyi Random Networks","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2601.06733","title":"Logic-Driven Semantic Communication for Resilient Multi-Agent Systems","created":"2026-01-11","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":"2605.06202","title":"Bandit Learning in General Open Multi-agent Systems","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.27076","title":"Cost of Structural Learning Under Censored Feedback: A Threshold-Bandit Approach","created":"2026-05-26","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}