{"total":102,"rows":[{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70,"area":null},{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2109.08075","title":"Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health","created":"2021-09-16","cited_by_count":43,"area":null},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2110.01463","title":"Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits","created":"2021-10-04","cited_by_count":31,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2103.00063","title":"Local Clustering in Contextual Multi-Armed Bandits","created":"2021-02-26","cited_by_count":29,"area":null},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28,"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":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"area":null},{"id":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2308.10808","title":"Graph Neural Bandits","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2202.04294","title":"Optimal Clustering with Bandit Feedback","created":"2022-02-09","cited_by_count":15,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2112.14233","title":"Multitask Learning and Bandits via Robust Statistics","created":"2021-12-28","cited_by_count":11,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2205.14174","title":"Private and Byzantine-Proof Cooperative Decision-Making","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2208.14865","title":"Federated Online Clustering of Bandits","created":"2022-08-31","cited_by_count":10,"area":null},{"id":"2309.00557","title":"Concentrated Differential Privacy for Bandits","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","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":"2202.13001","title":"Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2206.03644","title":"Neural Bandit with Arm Group Graph","created":"2022-06-08","cited_by_count":8,"area":null},{"id":"2201.13395","title":"Neural Collaborative Filtering Bandits via Meta Learning","created":"2022-01-31","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":"2406.08229","title":"GPT4Rec: Graph Prompt Tuning for Streaming Recommendation","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2605.10870","title":"Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2402.16312","title":"Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2108.01152","title":"Maximizing and Satisficing in Multi-armed Bandits with Graph Information","created":"2021-08-02","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":"2208.14555","title":"Dynamic Global Sensitivity for Differentially Private Contextual Bandits","created":"2022-08-30","cited_by_count":5,"area":null},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2402.10028","title":"Diffusion Models Meet Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":"diffusion"},{"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":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2205.08295","title":"Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization","created":"2022-05-17","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2403.00116","title":"Federated Linear Contextual Bandits with Heterogeneous Clients","created":"2024-02-29","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":"2507.17528","title":"Generalized Low-Rank Matrix Contextual Bandits with Graph Information","created":"2025-07-23","cited_by_count":4,"area":null},{"id":"2206.08556","title":"Thompson Sampling for Robust Transfer in Multi-Task Bandits","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2310.04768","title":"Online Corrupted User Detection and Regret Minimization","created":"2023-10-07","cited_by_count":3,"area":null},{"id":"2401.15062","title":"Expert with Clustering: Hierarchical Online Preference Learning Framework","created":"2024-01-26","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":"2501.14314","title":"Graph Feedback Bandits on Similar Arms: With and Without Graph Structures","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2310.10259","title":"Leveraging heterogeneous spillover in maximizing contextual bandit rewards","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2311.03376","title":"Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2405.11171","title":"Graph Feedback Bandits with Similar Arms","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2410.14586","title":"Neural Combinatorial Clustered Bandits for Recommendation Systems","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2502.15900","title":"Explaining the Success of Nearest Neighbor Methods in Prediction","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2511.18868","title":"KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits","created":"2025-11-24","cited_by_count":2,"area":"inference"},{"id":"2605.00489","title":"Revealing graph bandits for maximizing local influence","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2203.08027","title":"Natural Hierarchical Cluster Analysis by Nearest Neighbors with Near-Linear Time Complexity","created":"2022-03-15","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":"2307.03641","title":"Online Network Source Optimization with Graph-Kernel MAB","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2308.07857","title":"Impression-Aware Recommender Systems","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2309.08710","title":"Adaptive Sample Sharing for Multi Agent Linear Bandits","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2312.15549","title":"Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2410.12086","title":"Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.11794","title":"Competing Bandits in Decentralized Contextual Matching Markets","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2604.13738","title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2607.05465","title":"CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2104.07150","title":"When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2107.00161","title":"The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems","created":"2021-07-01","cited_by_count":0,"area":null},{"id":"2107.07438","title":"Convolutional Neural Bandit for Visual-aware Recommendation","created":"2021-07-02","cited_by_count":0,"area":null},{"id":"2111.08057","title":"Margin-Independent Online Multiclass Learning via Convex Geometry","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2112.00979","title":"Recommending with Recommendations","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2302.05765","title":"Adversarial Online Collaborative Filtering","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2305.01470","title":"Stochastic Contextual Bandits with Graph-based Contexts","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2308.10722","title":"Clustered Linear Contextual Bandits with Knapsacks","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2311.09483","title":"Adaptive Interventions with User-Defined Goals for Health Behavior Change","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2408.05843","title":"Online Matrix Completion: A Collaborative Approach with Hott Items","created":"2024-08-11","cited_by_count":0,"area":null},{"id":"2408.07897","title":"The Nah Bandit: Modeling User Non-compliance in Recommendation Systems","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2411.13690","title":"Multi-Agent Best Arm Identification in Stochastic Linear Bandits","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2502.01429","title":"An Algorithm for Fixed Budget Best Arm Identification with Combinatorial Exploration","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2505.03840","title":"CoCoB: Adaptive Collaborative Combinatorial Bandits for Online Recommendation","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2505.10147","title":"Near Optimal Best Arm Identification for Clustered Bandits","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.15943","title":"On the optimal regret of collaborative personalized linear bandits","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2508.02909","title":"Clus-UCB: A Near-Optimal Algorithm for Clustered Bandits","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.20076","title":"Anomaly Detection in Networked Bandits","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2512.12693","title":"Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2602.05690","title":"Almost Asymptotically Optimal Active Clustering Through Pairwise Observations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.15647","title":"Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing","created":"2026-03-04","cited_by_count":0,"area":"alignment"},{"id":"2604.25272","title":"Spectral bandits","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.25584","title":"Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.27917","title":"Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.25276","title":"FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.09366","title":"Beyond Binary: Continuous State Optimization with Graph-Structured Objectives","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":"100"}