{"total":37,"rows":[{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2203.17118","title":"Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank","created":"2022-03-31","cited_by_count":18,"area":null},{"id":"2402.01845","title":"Multi-Armed Bandits with Interference","created":"2024-02-02","cited_by_count":10,"area":null},{"id":"2306.02208","title":"Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits","created":"2023-06-03","cited_by_count":9,"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":"2107.11419","title":"Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits","created":"2021-07-23","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":"2206.08776","title":"Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms","created":"2022-06-17","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":"2301.10230","title":"Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints","created":"2023-01-24","cited_by_count":5,"area":null},{"id":"2104.05781","title":"Censored Semi-Bandits for Resource Allocation","created":"2021-04-12","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":"2605.20854","title":"Regret Analysis of Retry-Based Bandits","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2501.13535","title":"LITE: Efficiently Estimating Gaussian Probability of Maximality","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2102.10200","title":"A High Performance, Low Complexity Algorithm for Multi-Player Bandits Without Collision Sensing Information","created":"2021-02-19","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":"2207.01393","title":"Autonomous Drug Design with Multi-Armed Bandits","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2402.07391","title":"Replicability is Asymptotically Free in Multi-armed Bandits","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2202.05193","title":"Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2307.14549","title":"Adversarial Sleeping Bandit Problems with Multiple Plays: Algorithm and Ranking Application","created":"2023-07-27","cited_by_count":1,"area":null},{"id":"2407.15439","title":"Merit-based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays","created":"2024-07-22","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":"2506.06989","title":"A Control Function Framework for Mitigating Position Bias in Learning to Rank Systems","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2104.01078","title":"Blind Exploration and Exploitation of Stochastic Experts","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2106.02855","title":"Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2109.15228","title":"Adapting Bandit Algorithms for Settings with Sequentially Available Arms","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2110.14078","title":"Adversarial Online Learning with Variable Plays in the Pursuit-Evasion Game: Theoretical Foundations and Application in Connected and Automated Vehicle Cybersecurity","created":"2021-10-26","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","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":"2410.10679","title":"Combinatorial Multi-armed Bandits: Arm Selection via Group Testing","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2505.03840","title":"CoCoB: Adaptive Collaborative Combinatorial Bandits for Online Recommendation","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2507.20112","title":"Online Learning with Probing for Sequential User-Centric Selection","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2509.25824","title":"Decentralized Asynchronous Multi-player Bandits","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.21626","title":"Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing","created":"2025-12-25","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":"2605.25391","title":"A Context Augmented Multi-Play Multi-Armed Bandit Algorithm for Fast Channel Allocation in Opportunistic Spectrum Access","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}