{"total":64,"rows":[{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2307.08249","title":"Random Boxes Are Open-world Object Detectors","created":"2023-07-17","cited_by_count":24,"area":null},{"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":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22,"area":null},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2103.13929","title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","created":"2021-03-25","cited_by_count":21,"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":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"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":"2311.07565","title":"Exploration via linearly perturbed loss minimisation","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2105.09232","title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","created":"2021-05-19","cited_by_count":12,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2502.08870","title":"When and why randomised exploration works (in linear bandits)","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2403.00233","title":"Causal Bandits with General Causal Models and Interventions","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2307.10167","title":"VITS : Variational Inference Thompson Sampling for contextual bandits","created":"2023-07-19","cited_by_count":6,"area":null},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2411.03932","title":"Improved Regret of Linear Ensemble Sampling","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2402.05878","title":"Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2407.20124","title":"AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2201.09798","title":"IMO$^3$: Interactive Multi-Objective Off-Policy Optimization","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2411.05979","title":"Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2203.04192","title":"Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2311.14359","title":"Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2312.08559","title":"Fair Active Learning in Low-Data Regimes","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2510.10730","title":"Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2603.23140","title":"DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2104.05613","title":"An Efficient Algorithm for Deep Stochastic Contextual Bandits","created":"2021-04-12","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":"2209.08403","title":"Advertising Media and Target Audience Optimization via High-dimensional Bandits","created":"2022-09-17","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":"2403.06814","title":"{\\epsilon}-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2406.10686","title":"Graph Neural Thompson Sampling","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2412.02861","title":"An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2503.10836","title":"Exploiting Concavity Information in Gaussian Process Contextual Bandit Optimization","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2510.05023","title":"Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2601.20666","title":"Learning Contextual Runtime Monitors for Safe AI-Based Autonomy","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2202.10008","title":"Double Thompson Sampling in Finite stochastic Games","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2205.02944","title":"A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2312.15595","title":"Zero-Inflated Bandits","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2406.14071","title":"Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2501.19401","title":"DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary 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":"2510.17390","title":"Exploration via Feature Perturbation in Contextual Bandits","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2603.07005","title":"Combinatorial Allocation Bandits with Nonlinear Arm Utility","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.16755","title":"A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.00431","title":"Variance-sensitive Thompson sampling for generalised linear bandits, revisited","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.28616","title":"Randomized Exploration for Linear Bandits via Absolute Perturbations","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.13954","title":"Linear Ensemble Sampling with Smaller Ensembles","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}