{"total":68,"rows":[{"id":"2103.02735","title":"Fairness of Exposure in Stochastic Bandits","created":"2021-03-03","cited_by_count":43,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2106.13039","title":"Low-Latency Federated Learning over Wireless Channels with Differential Privacy","created":"2021-06-20","cited_by_count":25,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2106.07677","title":"Planning to Fairly Allocate: Probabilistic Fairness in the Restless Bandit Setting","created":"2021-06-14","cited_by_count":12,"area":null},{"id":"2206.03883","title":"Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits","created":"2022-06-08","cited_by_count":11,"area":null},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2206.03150","title":"Group Meritocratic Fairness in Linear Contextual Bandits","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2303.06396","title":"No-regret Algorithms for Fair Resource Allocation","created":"2023-03-11","cited_by_count":9,"area":null},{"id":"2208.09254","title":"Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Bandits","created":"2022-08-19","cited_by_count":8,"area":null},{"id":"2209.01126","title":"Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB","created":"2022-09-02","cited_by_count":8,"area":null},{"id":"2407.01795","title":"Honor Among Bandits: No-Regret Learning for Online Fair Division","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2102.07120","title":"Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment","created":"2021-02-14","cited_by_count":6,"area":null},{"id":"2304.05219","title":"BanditQ: Fair Bandits with Guaranteed Rewards","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2104.12037","title":"Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability","created":"2021-04-24","cited_by_count":5,"area":null},{"id":"2110.14621","title":"Fairer LP-based Online Allocation via Analytic Center","created":"2021-10-27","cited_by_count":5,"area":null},{"id":"2112.11818","title":"Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2207.13343","title":"Towards Soft Fairness in Restless Multi-Armed Bandits","created":"2022-07-27","cited_by_count":5,"area":null},{"id":"2301.05753","title":"Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2101.00257","title":"Efficient Learning-based Scheduling for Information Freshness in Wireless Networks","created":"2021-01-01","cited_by_count":4,"area":null},{"id":"2405.13919","title":"Fair Online Bilateral Trade","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2408.12845","title":"Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies","created":"2024-08-23","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":"2108.03297","title":"Joint AP Probing and Scheduling: A Contextual Bandit Approach","created":"2021-08-06","cited_by_count":3,"area":null},{"id":"2205.05659","title":"Ranked Prioritization of Groups in Combinatorial Bandit Allocation","created":"2022-05-11","cited_by_count":3,"area":null},{"id":"2408.17313","title":"Fair Best Arm Identification with Fixed Confidence","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2501.00924","title":"On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2501.07022","title":"Improved Regret Bounds for Online Fair Division with Bandit Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2107.11728","title":"Federated Learning with Fair Worker Selection: A Multi-Round Submodular Maximization Approach","created":"2021-07-25","cited_by_count":2,"area":null},{"id":"2110.02248","title":"Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2112.14338","title":"Socially-Optimal Mechanism Design for Incentivized Online Learning","created":"2021-12-29","cited_by_count":2,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"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":"2212.13585","title":"Online Learning for Adaptive Probing and Scheduling in Dense WLANs","created":"2022-12-27","cited_by_count":2,"area":null},{"id":"2502.03953","title":"Fairness Aware Reinforcement Learning via Proximal Policy Optimization","created":"2025-02-06","cited_by_count":2,"area":"deeprl"},{"id":"2302.09298","title":"Improving Fairness in Adaptive Social Exergames via Shapley Bandits","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2303.06552","title":"Energy Regularized RNNs for Solving Non-Stationary Bandit Problems","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2402.05575","title":"Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2402.06348","title":"Fairness of Exposure in Online Restless Multi-armed Bandits","created":"2024-02-09","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":"2505.05169","title":"Bandit Max-Min Fair Allocation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.19700","title":"Regret Analysis of Sleeping Competing Bandits","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2102.03051","title":"DEAL: Decremental Energy-Aware Learning in a Federated System","created":"2021-02-05","cited_by_count":0,"area":null},{"id":"2106.01624","title":"Sleeping Combinatorial Bandits","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2111.04272","title":"Identifying Best Fair Intervention","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2211.08311","title":"On Penalization in Stochastic Multi-armed Bandits","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2310.14164","title":"$\\alpha$-Fair Contextual Bandits","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2404.16920","title":"Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks","created":"2024-04-25","cited_by_count":0,"area":"deeprl"},{"id":"2408.14298","title":"Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2409.11442","title":"A Green Multi-Attribute Client Selection for Over-The-Air Federated Learning: A Grey-Wolf-Optimizer Approach","created":"2024-09-16","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":"2506.10313","title":"Collaborative Min-Max Regret in Grouped Multi-Armed Bandits","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2509.12457","title":"On the Regularity and Fairness of Combinatorial Multi-Armed Bandit","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.12523","title":"Multi-Armed Bandits with Minimum Aggregated Revenue Constraints","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2601.05956","title":"On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.05019","title":"A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.06361","title":"Envy-Free Allocation of Indivisible Goods via Noisy Queries","created":"2026-02-06","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":"2603.26647","title":"An LP-based Sampling Policy for Multi-Armed Bandits with Side-Observations and Stochastic Availability","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.00762","title":"Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback","created":"2026-05-01","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":"2605.27999","title":"Learning to Assign Prediction Tasks to Agents with Capacity Constraints","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.17489","title":"Online LLM Selection via Constrained Bandits with Time-Varying Demand","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.22935","title":"Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}