{"total":56,"rows":[{"id":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37,"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":"2101.01301","title":"Adversarial Combinatorial Bandits with General Non-linear Reward Functions","created":"2021-01-05","cited_by_count":14,"area":null},{"id":"2205.01889","title":"Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness","created":"2022-05-04","cited_by_count":13,"area":null},{"id":"2305.12402","title":"Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits","created":"2023-05-21","cited_by_count":13,"area":null},{"id":"2101.07957","title":"Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions","created":"2021-01-20","cited_by_count":9,"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":"2102.07800","title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2312.15427","title":"Semi-Bandit Learning for Monotone Stochastic Optimization","created":"2023-12-24","cited_by_count":8,"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":"2310.18465","title":"Nearly Minimax Optimal Submodular Maximization with Bandit Feedback","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2106.10166","title":"Problem Dependent View on Structured Thresholding Bandit Problems","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","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":"2102.12094","title":"Combinatorial Pure Exploration with Bottleneck Reward Function","created":"2021-02-24","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":"2102.04824","title":"A Multi-Arm Bandit Approach To Subset Selection Under Constraints","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2104.08615","title":"Conservative Contextual Combinatorial Cascading Bandit","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2105.10625","title":"Combinatorial Blocking Bandits with Stochastic Delays","created":"2021-05-22","cited_by_count":3,"area":null},{"id":"2305.16074","title":"Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2102.00321","title":"Recurrent Submodular Welfare and Matroid Blocking Bandits","created":"2021-01-30","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":"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":"2212.13585","title":"Online Learning for Adaptive Probing and Scheduling in Dense WLANs","created":"2022-12-27","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":"2407.05484","title":"Learning to Price Homogeneous Data","created":"2024-07-07","cited_by_count":2,"area":null},{"id":"2410.09597","title":"A Complete Characterization of Learnability for Stochastic Noisy Bandits","created":"2024-10-12","cited_by_count":2,"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":"2412.00798","title":"Combinatorial Rising Bandits","created":"2024-12-01","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":"2605.12646","title":"Learning to Decide with AI Assistance under Human-Alignment","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2104.06339","title":"Deep imagination is a close to optimal policy for planning in large decision trees under limited resources","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2105.03598","title":"Pure Exploration Bandit Problem with General Reward Functions Depending on Full Distributions","created":"2021-05-08","cited_by_count":0,"area":null},{"id":"2106.01624","title":"Sleeping Combinatorial Bandits","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2202.08302","title":"Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2210.05789","title":"Trading Off Resource Budgets for Improved Regret Bounds","created":"2022-10-11","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":"2303.03327","title":"Tight Bounds for $\\gamma$-Regret via the Decision-Estimation Coefficient","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2410.08578","title":"Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit","created":"2024-10-11","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":"2410.13109","title":"Latency-Aware Contextual Bandit: Application to Cryo-EM Data Collection","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2502.13467","title":"On the Sublinear Regret of Continuous K-Max Bandits","created":"2025-02-19","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":"2507.20112","title":"Online Learning with Probing for Sequential User-Centric Selection","created":"2025-07-27","cited_by_count":0,"area":null},{"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":"2509.12457","title":"On the Regularity and Fairness of Combinatorial Multi-Armed Bandit","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.21431","title":"Oracle-Efficient Combinatorial Semi-Bandits","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2601.00933","title":"LOFA: Online Influence Maximization under Full-Bandit Feedback using Lazy Forward Selection","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2605.10151","title":"Learning to Sparsify Stochastic Linear Bandits","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.14650","title":"Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals","created":"2026-06-12","cited_by_count":0,"area":"alignment"},{"id":"2607.11684","title":"Diversified Multinomial Logit Contextual Bandits","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.14557","title":"Selecting k Paths with the Minimum Longest Path Length in the Stochastic Semi-Bandit Setting","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.37932","title":"Learning When to Update: A Near-Optimal Timing Bandit Approach","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}