{"total":78,"rows":[{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"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":"2208.14837","title":"Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms","created":"2022-08-31","cited_by_count":15,"area":null},{"id":"2101.01301","title":"Adversarial Combinatorial Bandits with General Non-linear Reward Functions","created":"2021-01-05","cited_by_count":14,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2206.03520","title":"Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2204.12048","title":"Thompson Sampling for Bandit Learning in Matching Markets","created":"2022-04-26","cited_by_count":10,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"area":null},{"id":"2109.08467","title":"Online Learning of Network Bottlenecks via Minimax Paths","created":"2021-09-17","cited_by_count":9,"area":null},{"id":"2206.00494","title":"Incentivizing Combinatorial Bandit Exploration","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2111.02314","title":"Online Learning of Energy Consumption for Navigation of Electric Vehicles","created":"2021-11-03","cited_by_count":7,"area":null},{"id":"2111.04295","title":"The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2301.05182","title":"Thompson Sampling with Diffusion Generative Prior","created":"2023-01-12","cited_by_count":7,"area":"diffusion"},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2102.12722","title":"Combinatorial Bandits under Strategic Manipulations","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2106.05065","title":"Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2202.03704","title":"Budgeted Combinatorial Multi-Armed Bandits","created":"2022-02-08","cited_by_count":6,"area":null},{"id":"2302.11182","title":"When Combinatorial Thompson Sampling meets Approximation Regret","created":"2023-02-22","cited_by_count":6,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.00775","title":"ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning","created":"2025-02-02","cited_by_count":5,"area":null},{"id":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2102.05502","title":"On the Suboptimality of Thompson Sampling in High Dimensions","created":"2021-02-10","cited_by_count":4,"area":null},{"id":"2102.07254","title":"Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time","created":"2021-02-14","cited_by_count":4,"area":null},{"id":"2104.05781","title":"Censored Semi-Bandits for Resource Allocation","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2106.06712","title":"Simple Combinatorial Algorithms for Combinatorial Bandits: Corruptions and Approximations","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2108.00230","title":"Pure Exploration and Regret Minimization in Matching Bandits","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2407.14879","title":"Thompson Sampling Itself is Differentially Private","created":"2024-07-20","cited_by_count":4,"area":null},{"id":"2410.05856","title":"Stochastic Bandits for Egalitarian Assignment","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2501.19122","title":"FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2206.13192","title":"Differentially Private Federated Combinatorial Bandits with Constraints","created":"2022-06-27","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2402.15171","title":"Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2405.17968","title":"Matroid Semi-Bandits in Sublinear Time","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2510.23992","title":"Optimal Arm Elimination Algorithms for Combinatorial Bandits","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2111.14778","title":"Contextual Combinatorial Multi-output GP Bandits with Group Constraints","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2112.01141","title":"Risk-Aware Algorithms for Combinatorial Semi-Bandits","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2206.08144","title":"A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2308.10699","title":"Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach","created":"2023-08-21","cited_by_count":2,"area":null},{"id":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2506.19977","title":"Context Attribution with Multi-Armed Bandit Optimization","created":"2025-06-24","cited_by_count":2,"area":"rag"},{"id":"2508.18768","title":"Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2302.09440","title":"Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits","created":"2023-02-18","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":"2410.05441","title":"Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.23423","title":"Dynamic Information Sub-Selection for Decision Support","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2412.00798","title":"Combinatorial Rising Bandits","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2505.22254","title":"A Unified Online-Offline Framework for Co-Branding Campaign Recommendations","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.12490","title":"Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2602.11491","title":"Exploring Multiple High-Scoring Subspaces in Generative Flow Networks","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2604.13738","title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2106.01624","title":"Sleeping Combinatorial Bandits","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2208.01511","title":"Unimodal Mono-Partite Matching in a Bandit Setting","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2210.05977","title":"BORA: Bayesian Optimization for Resource Allocation","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2212.11603","title":"Sequential Decision Problems with Weak Feedback","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2301.07156","title":"A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2305.19691","title":"Constant or logarithmic regret in asynchronous multiplayer bandits","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2312.00099","title":"Online Influence Maximization: Concept and Algorithm","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2312.15595","title":"Zero-Inflated Bandits","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2401.06135","title":"A Distributed Neural Linear Thompson Sampling Framework to Achieve URLLC in Industrial IoT","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2402.15703","title":"Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2410.10679","title":"Combinatorial Multi-armed Bandits: Arm Selection via Group Testing","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2503.12285","title":"A Resilience Framework for Bi-Criteria Combinatorial Optimization with Bandit Feedback","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2508.06247","title":"Near-Optimal Regret for Efficient Stochastic Combinatorial Semi-Bandits","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.09933","title":"Multi-Play Combinatorial Semi-Bandit Problem","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2510.21431","title":"Oracle-Efficient Combinatorial Semi-Bandits","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.10938","title":"Cascading Bandits With Feedback","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.24231","title":"Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.07005","title":"Combinatorial Allocation Bandits with Nonlinear Arm Utility","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2604.14908","title":"Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19672","title":"Budgeted Online Influence Maximization","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.09277","title":"Worst-Case Regret Bounds for Combinatorial Thompson Sampling in Sleeping Semi-Bandits","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.10289","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.15440","title":"Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}