{"total":44,"rows":[{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2103.00063","title":"Local Clustering in Contextual Multi-Armed Bandits","created":"2021-02-26","cited_by_count":29,"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":"2308.10808","title":"Graph Neural Bandits","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2205.14174","title":"Private and Byzantine-Proof Cooperative Decision-Making","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2208.14865","title":"Federated Online Clustering of Bandits","created":"2022-08-31","cited_by_count":10,"area":null},{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2206.03644","title":"Neural Bandit with Arm Group Graph","created":"2022-06-08","cited_by_count":8,"area":null},{"id":"2201.13395","title":"Neural Collaborative Filtering Bandits via Meta Learning","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2304.02572","title":"Evaluating Online Bandit Exploration In Large-Scale Recommender System","created":"2023-04-05","cited_by_count":7,"area":null},{"id":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2406.08229","title":"GPT4Rec: Graph Prompt Tuning for Streaming Recommendation","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2205.09899","title":"Breaking the $\\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2406.10131","title":"Linear Contextual Bandits with Hybrid Payoff: Revisited","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2106.08902","title":"Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2310.07596","title":"Prospective Side Information for Latent MDPs","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2403.00116","title":"Federated Linear Contextual Bandits with Heterogeneous Clients","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2507.17528","title":"Generalized Low-Rank Matrix Contextual Bandits with Graph Information","created":"2025-07-23","cited_by_count":4,"area":null},{"id":"2401.15062","title":"Expert with Clustering: Hierarchical Online Preference Learning Framework","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2310.10259","title":"Leveraging heterogeneous spillover in maximizing contextual bandit rewards","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2311.03376","title":"Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2209.06128","title":"A Scalable Recommendation Engine for New Users and Items","created":"2022-09-06","cited_by_count":1,"area":null},{"id":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2309.08710","title":"Adaptive Sample Sharing for Multi Agent Linear Bandits","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2410.12086","title":"Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2104.07150","title":"When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2111.08057","title":"Margin-Independent Online Multiclass Learning via Convex Geometry","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2212.13915","title":"Demystifying Advertising Campaign Bid Recommendation: A Constraint target CPA Goal Optimization","created":"2022-12-26","cited_by_count":0,"area":null},{"id":"2305.01470","title":"Stochastic Contextual Bandits with Graph-based Contexts","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2308.10722","title":"Clustered Linear Contextual Bandits with Knapsacks","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2311.09483","title":"Adaptive Interventions with User-Defined Goals for Health Behavior Change","created":"2023-11-16","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":"2604.25272","title":"Spectral bandits","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2610.18258","title":"Optimal Online Regret for Context-Lumpable Bandits","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}