{"total":50,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27,"area":null},{"id":"2110.13282","title":"The Pareto Frontier of model selection for general Contextual Bandits","created":"2021-10-25","cited_by_count":24,"area":null},{"id":"2202.06151","title":"Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits","created":"2022-02-12","cited_by_count":22,"area":null},{"id":"2110.12615","title":"Linear Contextual Bandits with Adversarial Corruptions","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2206.14912","title":"Best of Both Worlds Model Selection","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2306.02869","title":"Data-Driven Online Model Selection With Regret Guarantees","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2106.02979","title":"Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2112.13254","title":"On Dynamic Pricing with Covariates","created":"2021-12-25","cited_by_count":10,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2504.13938","title":"Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection","created":"2025-04-15","cited_by_count":8,"area":null},{"id":"2203.04274","title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2302.08345","title":"Linear Bandits with Memory: from Rotting to Rising","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2404.09494","title":"On the Necessity of Collaboration for Online Model Selection with Decentralized Data","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2106.06483","title":"Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2111.04688","title":"Universal and data-adaptive algorithms for model selection in linear contextual bandits","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2205.09899","title":"Breaking the $\\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2304.13830","title":"Adaptation to Misspecified Kernel Regularity in Kernelised Bandits","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2306.11017","title":"High-dimensional Contextual Bandit Problem without Sparsity","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2106.08902","title":"Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2407.01566","title":"A Parametric Contextual Online Learning Theory of Brokerage","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2507.11891","title":"Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2402.07588","title":"Understanding Model Selection For Learning In Strategic Environments","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2406.01192","title":"Sparsity-Agnostic Linear Bandits with Adaptive Adversaries","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2302.09440","title":"Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2401.10478","title":"Budgeted Online Model Selection and Fine-Tuning via Federated Learning","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2409.13888","title":"Causal Feature Selection Method for Contextual Multi-Armed Bandits in Recommender System","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.06069","title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2505.16221","title":"LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead","created":"2025-05-22","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":"2609.05820","title":"Online Learning with LLM Experts from Limited Feedback","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2102.05164","title":"Nonstochastic Bandits with Infinitely Many Experts","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2609.06514","title":"Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}