{"total":23,"rows":[{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10,"area":null},{"id":"2103.00368","title":"PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2305.17071","title":"Adversarial Attacks on Online Learning to Rank with Click Feedback","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2305.19218","title":"Adversarial Attacks on Online Learning to Rank with Stochastic Click Models","created":"2023-05-30","cited_by_count":6,"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":"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":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2410.02126","title":"BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2111.00735","title":"Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rank","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","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":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2402.14013","title":"Misalignment, Learning, and Ranking: Harnessing Users Limited Attention","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2509.22855","title":"Observation-Free Attacks on Online Learning to Rank","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.03074","title":"Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2609.06670","title":"Data Efficient Sample Selection for In-Context Learning","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}