{"total":78,"rows":[{"id":"2103.02735","title":"Fairness of Exposure in Stochastic Bandits","created":"2021-03-03","cited_by_count":43,"area":null},{"id":"2107.06720","title":"Fairness in Ranking under Uncertainty","created":"2021-07-14","cited_by_count":27,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2108.09435","title":"Fairness-Aware Online Meta-learning","created":"2021-08-21","cited_by_count":19,"area":null},{"id":"2206.04101","title":"What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2205.13930","title":"Fairness and Welfare Quantification for Regret in Multi-Armed Bandits","created":"2022-05-27","cited_by_count":17,"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":"2111.10476","title":"Towards Return Parity in Markov Decision Processes","created":"2021-11-19","cited_by_count":13,"area":null},{"id":"2208.12584","title":"Socially Fair Reinforcement Learning","created":"2022-08-26","cited_by_count":13,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2109.08792","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2203.13423","title":"Modeling Attrition in Recommender Systems with Departing Bandits","created":"2022-03-25","cited_by_count":11,"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":"2306.01007","title":"Towards Fair Disentangled Online Learning for Changing Environments","created":"2023-05-31","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":"2205.15436","title":"Uncertainty Quantification for Fairness in Two-Stage Recommender Systems","created":"2022-05-30","cited_by_count":10,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","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":"2310.02023","title":"Nash Regret Guarantees for Linear Bandits","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2405.06909","title":"Fairness in Reinforcement Learning: A Survey","created":"2024-05-11","cited_by_count":9,"area":"deeprl"},{"id":"2205.08875","title":"Multi-disciplinary fairness considerations in machine learning for clinical trials","created":"2022-05-18","cited_by_count":8,"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":"2302.01377","title":"Learning with Exposure Constraints in Recommendation Systems","created":"2023-02-02","cited_by_count":8,"area":null},{"id":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","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":"2109.08934","title":"Fairness Maximization among Offline Agents in Online-Matching Markets","created":"2021-09-18","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":"2308.09726","title":"Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital Health","created":"2023-08-17","cited_by_count":6,"area":null},{"id":"2412.10751","title":"p-Mean Regret for Stochastic Bandits","created":"2024-12-14","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":"2110.13054","title":"Adaptive Data Debiasing through Bounded Exploration","created":"2021-10-25","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":"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":"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":"2406.06736","title":"Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges","created":"2024-06-10","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":"2510.21312","title":"Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2203.09784","title":"The price of unfairness in linear bandits with biased feedback","created":"2022-03-18","cited_by_count":3,"area":null},{"id":"2211.06569","title":"RISE: Robust Individualized Decision Learning with Sensitive Variables","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2303.00799","title":"Fairness for Workers Who Pull the Arms: An Index Based Policy for Allocation of Restless Bandit Tasks","created":"2023-03-01","cited_by_count":3,"area":null},{"id":"2305.13293","title":"Time Fairness in Online Knapsack Problems","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2404.10942","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"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":"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":"2402.11338","title":"Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach","created":"2024-02-17","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":"2205.04619","title":"Risk Preferences of Learning Algorithms","created":"2022-05-10","cited_by_count":1,"area":null},{"id":"2301.12278","title":"Pragmatic Fairness: Developing Policies with Outcome Disparity Control","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2402.03531","title":"Fairness and Privacy Guarantees in Federated Contextual Bandits","created":"2024-02-05","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":"2407.07350","title":"Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement","created":"2024-07-10","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":"2506.14988","title":"Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.11070","title":"Your Recourse, My Loss? Algorithmic Recourse under Shared Constraints","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2111.04272","title":"Identifying Best Fair Intervention","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2211.04568","title":"Towards Algorithmic Fairness in Space-Time: Filling in Black Holes","created":"2022-11-08","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":"2404.12186","title":"Privacy-Preserving UCB Decision Process Verification via zk-SNARKs","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2411.04295","title":"Fairness with Exponential Weights","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2502.15240","title":"Multi-agent Multi-armed Bandits with Minimum Reward Guarantee Fairness","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2504.08151","title":"Adaptive Bounded Exploration and Intermediate Actions for Data Debiasing","created":"2025-04-10","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":"2510.27123","title":"Group-Sensitive Offline Contextual Bandits","created":"2025-10-31","cited_by_count":0,"area":"offlinerl"},{"id":"2601.10600","title":"Procedural Fairness in Multi-Agent Bandits","created":"2026-01-15","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":"2606.01159","title":"Fairness in two-player zero-sum games with bandit feedback","created":"2026-05-31","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},{"id":"2610.20514","title":"Bayesian Learning to Select Fair Classifiers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}