{"total":19,"rows":[{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2110.10018","title":"Dynamic pricing and assortment under a contextual MNL demand","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20,"area":null},{"id":"2502.10020","title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","created":"2025-02-14","cited_by_count":15,"area":null},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2406.09882","title":"Harm Mitigation in Recommender Systems under User Preference Dynamics","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2402.08126","title":"Contextual Multinomial Logit Bandits with General Value Functions","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2502.06777","title":"Learning an Optimal Assortment Policy under Observational Data","created":"2025-02-10","cited_by_count":4,"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":"2504.02324","title":"Dynamic Assortment Selection and Pricing with Censored Preference Feedback","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2109.02519","title":"Online Learning of Independent Cascade Models with Node-level Feedback","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2312.12400","title":"New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2501.19277","title":"On Pareto Optimality for Parametric Choice Bandits","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2509.04194","title":"Stochastic Matching Bandits with Rare Optimization Updates","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2601.06913","title":"Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2605.25592","title":"Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.11684","title":"Diversified Multinomial Logit Contextual Bandits","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}