{"total":79,"rows":[{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"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":"2303.17110","title":"Contextual Combinatorial Bandits with Probabilistically Triggered Arms","created":"2023-03-30","cited_by_count":18,"area":null},{"id":"2206.01995","title":"Combinatorial Causal Bandits","created":"2022-06-04","cited_by_count":16,"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":"2105.04373","title":"Combinatorial Multi-armed Bandits for Resource Allocation","created":"2021-05-10","cited_by_count":10,"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":"2106.03403","title":"Network Inference and Influence Maximization from Samples","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2107.07322","title":"A unified framework for bandit multiple testing","created":"2021-07-15","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":"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":"2201.12408","title":"Networked Restless Multi-Armed Bandits for Mobile Interventions","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2301.13392","title":"Combinatorial Causal Bandits without Graph Skeleton","created":"2023-01-31","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":"2402.01400","title":"Query-Efficient Correlation Clustering with Noisy Oracle","created":"2024-02-02","cited_by_count":7,"area":null},{"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":"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":"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":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2503.07555","title":"Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference","created":"2025-03-10","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":"2212.12923","title":"Linear Combinatorial Semi-Bandit with Causally Related Rewards","created":"2022-12-25","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":"2102.04824","title":"A Multi-Arm Bandit Approach To Subset Selection Under Constraints","created":"2021-02-09","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":"2205.05659","title":"Ranked Prioritization of Groups in Combinatorial Bandit Allocation","created":"2022-05-11","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":"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":"2505.21938","title":"Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection","created":"2025-05-28","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":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2305.15428","title":"Online Influence Maximization under Decreasing Cascade Model","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2310.05308","title":"Adversarial Attacks on Combinatorial Multi-Armed Bandits","created":"2023-10-08","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":"2411.03270","title":"Stable Matching with Ties: Approximation Ratios and Learning","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2512.21925","title":"Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2605.00489","title":"Revealing graph bandits for maximizing local influence","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2109.02519","title":"Online Learning of Independent Cascade Models with Node-level Feedback","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2109.06077","title":"Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2110.05724","title":"Query-Reward Tradeoffs in Multi-Armed Bandits","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2208.10627","title":"Targeted Advertising on Social Networks Using Online Variational Tensor Regression","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2307.09093","title":"Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2307.14208","title":"Online Modeling and Monitoring of Dependent Processes under Resource Constraints","created":"2023-07-26","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":"2402.13079","title":"Mode Estimation with Partial Feedback","created":"2024-02-20","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":"2410.23423","title":"Dynamic Information Sub-Selection for Decision Support","created":"2024-10-30","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":"2509.15515","title":"LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference","created":"2025-09-19","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":"2607.13686","title":"Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2201.05231","title":"Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version)","created":"2022-01-13","cited_by_count":0,"area":"diffusion"},{"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":"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":"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":"2404.00371","title":"From Learning to Analytics: Improving Model Efficacy with Goal-Directed Client Selection","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2404.13737","title":"Stochastic Multi-round Submodular Optimization with Budget","created":"2024-04-21","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":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.05844","title":"Online Budget Allocation with Censored Semi-Bandit Feedback","created":"2025-08-07","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":"2512.21626","title":"Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.01179","title":"Adaptive Scheduling: A Reinforcement Learning Whittle Index Approach for Wireless Sensor Networks","created":"2026-01-03","cited_by_count":0,"area":"deeprl"},{"id":"2604.19672","title":"Budgeted Online Influence Maximization","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","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},{"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}