{"total":79,"rows":[{"id":"2405.16122","title":"Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars","created":"2024-05-25","cited_by_count":37,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2106.03365","title":"Generalized Linear Bandits with Local Differential Privacy","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2211.12612","title":"Transfer Learning for Contextual Multi-armed Bandits","created":"2022-11-22","cited_by_count":24,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2102.01229","title":"Doubly robust Thompson sampling for linear payoffs","created":"2021-02-01","cited_by_count":21,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"area":null},{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2406.19317","title":"Jump Starting Bandits with LLM-Generated Prior Knowledge","created":"2024-06-27","cited_by_count":12,"area":null},{"id":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2112.14233","title":"Multitask Learning and Bandits via Robust Statistics","created":"2021-12-28","cited_by_count":11,"area":null},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11,"area":null},{"id":"2109.11679","title":"Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2306.06250","title":"Strategic Apple Tasting","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2408.09655","title":"Contextual Bandits for Unbounded Context Distributions","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2102.07030","title":"Diffusion Approximations for a Class of Sequential Testing Problems","created":"2021-02-13","cited_by_count":7,"area":null},{"id":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2205.15100","title":"Meta Representation Learning with Contextual Linear Bandits","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2206.05404","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2302.07425","title":"Bandit Social Learning: Exploration under Myopic Behavior","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2502.17292","title":"Joint Value Estimation and Bidding in Repeated First-Price Auctions","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2605.08866","title":"Tight Generalization Bounds for Noiseless Inverse Optimization","created":"2026-05-09","cited_by_count":6,"area":null},{"id":"2204.11910","title":"Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2211.15381","title":"Incentive-Aware Recommender Systems in Two-Sided Markets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2402.17732","title":"Batched Nonparametric Contextual Bandits","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2204.04773","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","created":"2022-04-10","cited_by_count":2,"area":null},{"id":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2108.12547","title":"Dynamic Selection in Algorithmic Decision-making","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2206.08111","title":"On Private Online Convex Optimization: Optimal Algorithms in $\\ell_p$-Geometry and High Dimensional Contextual Bandits","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2209.07154","title":"Risk-aware linear bandits with convex loss","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2209.08403","title":"Advertising Media and Target Audience Optimization via High-dimensional Bandits","created":"2022-09-17","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":"2410.17086","title":"Exploration and Persuasion","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2501.03865","title":"Truthful mechanisms for linear bandit games with private contexts","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2510.22654","title":"Managing Self-Learning Experts under Per-Round Budget Constraints","created":"2025-10-26","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":"2603.21716","title":"Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits?","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2110.01072","title":"Active Learning for Contextual Search with Binary Feedbacks","created":"2021-10-03","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":"2306.17329","title":"Kernel $\\epsilon$-Greedy for Multi-Armed Bandits with Covariates","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2405.20642","title":"Learning Under Moral Hazard with Instrumental Regression and Generalized Method of Moments","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2409.09199","title":"Batched Online Contextual Sparse Bandits with Sequential Inclusion of Features","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.03926","title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2506.05265","title":"Teaming in the AI Era: AI-Augmented Frameworks for Forming, Simulating, and Optimizing Human Teams","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.01924","title":"Non-Linear Model-Based Sequential Decision-Making in Agriculture","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.07424","title":"Best-of-Both Worlds for linear contextual bandits with paid observations","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.15483","title":"Fast Best-in-Class Regret for Contextual Bandits","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.26000","title":"Infrequent Exploration in Linear Bandits","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.00943","title":"Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.20465","title":"Prior-Agnostic Incentive-Compatible Exploration","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10151","title":"Learning to Sparsify Stochastic Linear Bandits","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.31449","title":"Contextual Slate GLM Bandits with Limited Adaptivity","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.28718","title":"Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30321","title":"Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.35622","title":"Elicitation and Decision Geometry in Single-Index Bandits","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38914","title":"Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}