{"total":23,"rows":[{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2107.07106","title":"Online Learning for Recommendations at Grubhub","created":"2021-07-15","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":"2104.15046","title":"Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sampling","created":"2021-04-30","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":"2110.04127","title":"Deep Upper Confidence Bound Algorithm for Contextual Bandit Ranking of Information Selection","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2402.15171","title":"Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"area":null},{"id":"2206.14648","title":"Two-Stage Neural Contextual Bandits for Personalised News Recommendation","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2201.13287","title":"Top-K Ranking Deep Contextual Bandits for Information Selection Systems","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2406.02515","title":"Uncertainty of Joint Neural Contextual Bandit","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2509.00109","title":"Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.26284","title":"Empirical Bayesian Multi-Bandit Learning","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2202.00146","title":"Evaluating Deep Vs. Wide & Deep Learners As Contextual Bandits For Personalized Email Promo Recommendations","created":"2022-01-31","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2309.14046","title":"Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2310.04855","title":"Epsilon non-Greedy: A Bandit Approach for Unbiased Recommendation via Uniform Data","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2406.14071","title":"Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2408.13399","title":"Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2604.26651","title":"The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.04603","title":"Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval","created":"2026-06-03","cited_by_count":0,"area":null}],"next_cursor":null}