{"total":52,"rows":[{"id":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"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":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"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":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2101.12506","title":"Learning User Preferences in Non-Stationary Environments","created":"2021-01-29","cited_by_count":10,"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":"2402.11156","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","created":"2024-02-17","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":"2309.08634","title":"Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2404.17709","title":"Low-rank Matrix Bandits with Heavy-tailed Rewards","created":"2024-04-26","cited_by_count":7,"area":null},{"id":"2302.04441","title":"Multi-task Representation Learning for Pure Exploration in Linear Bandits","created":"2023-02-09","cited_by_count":6,"area":null},{"id":"2402.15739","title":"Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery","created":"2024-02-24","cited_by_count":6,"area":null},{"id":"2409.16499","title":"Learning Linear Dynamics from Bilinear Observations","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2410.02068","title":"Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2110.12160","title":"Multi-armed Bandit Algorithm against Strategic Replication","created":"2021-10-23","cited_by_count":5,"area":null},{"id":"2305.03884","title":"On High-dimensional and Low-rank Tensor Bandits","created":"2023-05-06","cited_by_count":5,"area":null},{"id":"2311.00327","title":"Multi-task Representation Learning for Pure Exploration in Bilinear Bandits","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2202.00805","title":"Context Uncertainty in Contextual Bandits with Applications to Recommender Systems","created":"2022-02-01","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":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","cited_by_count":3,"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":"2404.17592","title":"Low-Rank Online Dynamic Assortment with Dual Contextual Information","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2510.16208","title":"Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2510.21119","title":"Leveraging semantic similarity for experimentation with AI-generated treatments","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2608.04324","title":"Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits","created":"2026-08-05","cited_by_count":2,"area":null},{"id":"2205.05820","title":"Representation Learning for Context-Dependent Decision-Making","created":"2022-05-12","cited_by_count":1,"area":null},{"id":"2206.00466","title":"An $\\alpha$-No-Regret Algorithm For Graphical Bilinear Bandits","created":"2022-06-01","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":"2302.09440","title":"Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits","created":"2023-02-18","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":"2501.10722","title":"A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits","created":"2025-01-18","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":"2605.09454","title":"Optimal Regret for Single Index Bandits","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2605.20269","title":"Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2112.00979","title":"Recommending with Recommendations","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2112.06362","title":"Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2302.05765","title":"Adversarial Online Collaborative Filtering","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2406.15713","title":"Efficient Low-rank Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization","created":"2024-06-22","cited_by_count":0,"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":"2502.01012","title":"Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2605.25584","title":"Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.27917","title":"Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.11661","title":"Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.33025","title":"Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors","created":"2026-09-26","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}