{"total":113,"rows":[{"id":"2206.13687","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","created":"2022-06-28","cited_by_count":108,"area":null},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2110.03177","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","created":"2021-10-07","cited_by_count":44,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"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":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2310.02905","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","created":"2023-10-02","cited_by_count":30,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","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":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2308.10808","title":"Graph Neural Bandits","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2205.14309","title":"Federated Neural Bandits","created":"2022-05-28","cited_by_count":17,"area":null},{"id":"2205.14775","title":"An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge","created":"2022-05-29","cited_by_count":17,"area":null},{"id":"2306.00242","title":"Combinatorial Neural Bandits","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2411.01410","title":"PageRank Bandits for Link Prediction","created":"2024-11-03","cited_by_count":14,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2110.15458","title":"Open Problem: Tight Online Confidence Intervals for RKHS Elements","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2310.05373","title":"Quantum Bayesian Optimization","created":"2023-10-09","cited_by_count":12,"area":null},{"id":"2210.00423","title":"Improved Algorithms for Neural Active Learning","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2110.12122","title":"Quantifying Epistemic Uncertainty in Deep Learning","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2306.05674","title":"Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks","created":"2023-06-09","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":"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":"2211.09100","title":"Global Optimization with Parametric Function Approximation","created":"2022-11-16","cited_by_count":7,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","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":"2206.00099","title":"Provably and Practically Efficient Neural Contextual Bandits","created":"2022-05-31","cited_by_count":6,"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":"2310.00137","title":"On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective","created":"2023-09-29","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":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2404.16115","title":"Online Personalizing White-box LLMs Generation with Neural Bandits","created":"2024-04-24","cited_by_count":5,"area":null},{"id":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2112.11136","title":"Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction","created":"2021-12-21","cited_by_count":4,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2402.06963","title":"Tree Ensembles for Contextual Bandits","created":"2024-02-10","cited_by_count":4,"area":null},{"id":"2406.12835","title":"Influence Maximization via Graph Neural Bandits","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2408.12845","title":"Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies","created":"2024-08-23","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":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2510.25808","title":"PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2212.13667","title":"Learning When to Use Adaptive Adversarial Image Perturbations against Autonomous Vehicles","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2401.06173","title":"Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization","created":"2024-01-08","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":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"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":"2206.08144","title":"A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2303.01682","title":"Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks","created":"2023-03-03","cited_by_count":2,"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":"2405.07331","title":"Stochastic Bandits with ReLU Neural Networks","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2409.00561","title":"Multi-Task Combinatorial Bandits for Budget Allocation","created":"2024-08-31","cited_by_count":2,"area":null},{"id":"2410.06333","title":"Batched Bayesian optimization by maximizing the probability of including the optimum","created":"2024-10-08","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":"2503.03023","title":"Quantum Non-Linear Bandit Optimization","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2504.07247","title":"Resource-efficient Inference with Foundation Model Programs","created":"2025-04-09","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":"2510.01471","title":"Fine-tuning LLMs with variational Bayesian last layer for high-dimensional Bayesian optimization","created":"2025-10-01","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":"2111.03543","title":"Empirical analysis of representation learning and exploration in neural kernel bandits","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2303.13407","title":"Adaptive Endpointing with Deep Contextual Multi-armed Bandits","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2310.07786","title":"Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling","created":"2023-10-11","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":"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":"2412.04484","title":"Epinet for Content Cold Start","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2505.14102","title":"High-dimensional Nonparametric Contextual Bandit Problem","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.23720","title":"COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents","created":"2025-05-29","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":"2506.21894","title":"Thompson Sampling in Function Spaces via Neural Operators","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2601.02870","title":"Quantum-Enhanced Neural Contextual Bandit Algorithms","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2605.13160","title":"Kernel-based guarantees for nonlinear parametric models in Bayesian optimization","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.22518","title":"PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2609.13564","title":"When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2106.15128","title":"Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit","created":"2021-06-29","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":"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":"2212.05190","title":"Neural Bandits for Data Mining: Searching for Dangerous Polypharmacy","created":"2022-12-10","cited_by_count":0,"area":null},{"id":"2310.16323","title":"Personalized Federated X -armed Bandit","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","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":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.08773","title":"Counterfactual Inference under Thompson Sampling","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2504.12086","title":"Neural Contextual Bandits Under Delayed Feedback Constraints","created":"2025-04-16","cited_by_count":0,"area":null}],"next_cursor":"100"}