{"total":13,"rows":[{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","cited_by_count":15,"area":null},{"id":"2311.04402","title":"Likelihood Ratio Confidence Sets for Sequential Decision Making","created":"2023-11-08","cited_by_count":10,"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":"2502.06806","title":"Logits are All We Need to Adapt Closed Models","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2310.14751","title":"Efficient and Interpretable Bandit Algorithms","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2404.08846","title":"Experimental Design for Active Transductive Inference in Large Language Models","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2610.04039","title":"Adaptive Partitioning Schemes for Optimistic Optimization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.17760","title":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}