{"total":23,"rows":[{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2102.09626","title":"A Simple Unified Framework for High Dimensional Bandit Problems","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2401.07298","title":"Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2106.01660","title":"Bandit Phase Retrieval","created":"2021-06-03","cited_by_count":12,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2310.06793","title":"Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning","created":"2023-10-10","cited_by_count":10,"area":null},{"id":"2209.03997","title":"Online Low Rank Matrix Completion","created":"2022-09-08","cited_by_count":9,"area":null},{"id":"2110.12160","title":"Multi-armed Bandit Algorithm against Strategic Replication","created":"2021-10-23","cited_by_count":5,"area":null},{"id":"2106.12200","title":"Random Effect Bandits","created":"2021-06-23","cited_by_count":4,"area":null},{"id":"2108.00230","title":"Pure Exploration and Regret Minimization in Matching Bandits","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","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":"2507.17528","title":"Generalized Low-Rank Matrix Contextual Bandits with Graph Information","created":"2025-07-23","cited_by_count":4,"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":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2306.12383","title":"Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms","created":"2023-06-21","cited_by_count":2,"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":"2311.01771","title":"Efficient Generalized Low-Rank Tensor Contextual Bandits","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2412.02529","title":"Active learning of neural population dynamics using two-photon holographic optogenetics","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2510.00803","title":"Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2408.05843","title":"Online Matrix Completion: A Collaborative Approach with Hott Items","created":"2024-08-11","cited_by_count":0,"area":null},{"id":"2605.02458","title":"Active multiple matrix completion with adaptive confidence sets","created":"2026-05-04","cited_by_count":0,"area":null}],"next_cursor":null}