{"total":23,"rows":[{"id":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","cited_by_count":14,"area":null},{"id":"2202.01914","title":"Tsetlin Machine for Solving Contextual Bandit Problems","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2311.02268","title":"LLMs-augmented Contextual Bandit","created":"2023-11-03","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":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2203.15629","title":"Stochastic Conservative Contextual Linear Bandits","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2106.15808","title":"Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2112.11136","title":"Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction","created":"2021-12-21","cited_by_count":4,"area":null},{"id":"2503.08961","title":"Multiplayer Information Asymmetric Contextual Bandits","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2106.10898","title":"BanditMF: Multi-Armed Bandit Based Matrix Factorization Recommender System","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2202.02906","title":"Universality of parametric Coupling Flows over parametric diffeomorphisms","created":"2022-02-07","cited_by_count":2,"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":"2401.11565","title":"Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2104.05613","title":"An Efficient Algorithm for Deep Stochastic Contextual Bandits","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2111.03543","title":"Empirical analysis of representation learning and exploration in neural kernel bandits","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2310.07786","title":"Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2310.11188","title":"Adversarial Bandits with Multi-User Delayed Feedback: Theory and Application","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2101.00001","title":"Etat de l'art sur l'application des bandits multi-bras","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2305.04086","title":"Efficient Learning for Selecting Top-m Context-Dependent Designs","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2401.03059","title":"Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach","created":"2024-01-05","cited_by_count":0,"area":null}],"next_cursor":null}