{"total":60,"rows":[{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2211.05732","title":"The Sample Complexity of Online Contract Design","created":"2022-11-10","cited_by_count":35,"area":null},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2302.10805","title":"Repeated Bilateral Trade Against a Smoothed Adversary","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2305.18543","title":"Robust Lipschitz Bandits to Adversarial Corruptions","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2307.09478","title":"The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations","created":"2023-07-14","cited_by_count":15,"area":null},{"id":"2403.12948","title":"On Safety in Safe Bayesian Optimization","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2412.17622","title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2210.00025","title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2110.15843","title":"Adaptive Discretization in Online Reinforcement Learning","created":"2021-10-29","cited_by_count":12,"area":null},{"id":"2209.12013","title":"Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem","created":"2022-09-24","cited_by_count":12,"area":null},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2105.04373","title":"Combinatorial Multi-armed Bandits for Resource Allocation","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","cited_by_count":10,"area":null},{"id":"2305.11381","title":"Online Learning in a Creator Economy","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2309.08634","title":"Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2405.20678","title":"No-Regret Learning for Fair Multi-Agent Social Welfare Optimization","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2102.01977","title":"Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates","created":"2021-02-03","cited_by_count":7,"area":null},{"id":"2106.08598","title":"Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domains by Adaptive Discretization","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2509.22563","title":"Nearly Tight Regret Bounds for Profit Maximization in Bilateral Trade","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2109.05829","title":"Zeroth-order non-convex learning via hierarchical dual averaging","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2203.06297","title":"Instance-Dependent Regret Analysis of Kernelized Bandits","created":"2022-03-12","cited_by_count":5,"area":null},{"id":"2409.07819","title":"Selling Joint Ads: A Regret Minimization Perspective","created":"2024-09-12","cited_by_count":5,"area":null},{"id":"2403.07143","title":"Harnessing the Continuous Structure: Utilizing the First-order Approach in Online Contract Design","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2504.02251","title":"Quantum Lipschitz Bandits","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2302.08012","title":"Equilibrium of Data Markets with Externality","created":"2023-02-16","cited_by_count":3,"area":null},{"id":"2308.00978","title":"Certified Multi-Fidelity Zeroth-Order Optimization","created":"2023-08-02","cited_by_count":3,"area":null},{"id":"2312.04653","title":"Learning Thresholds with Latent Values and Censored Feedback","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2503.08004","title":"Multiplayer Information Asymmetric Bandits in Metric Spaces","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2110.07232","title":"Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2207.01393","title":"Autonomous Drug Design with Multi-Armed Bandits","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2508.19466","title":"Incentivized Lipschitz Bandits","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2602.10868","title":"The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2108.13810","title":"Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations","created":"2021-08-31","cited_by_count":1,"area":null},{"id":"2210.01295","title":"Max-Quantile Grouped Infinite-Arm Bandits","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2212.07524","title":"Invariant Lipschitz Bandits: A Side Observation Approach","created":"2022-12-14","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":"2510.00309","title":"Lipschitz Bandits with Stochastic Delayed Feedback","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2602.16965","title":"Multi-Agent Lipschitz Bandits","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.00523","title":"Lipschitz Dueling Bandits over Continuous Action Spaces","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.12664","title":"Profit Maximization in Bilateral Trade against a Smooth Adversary","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2205.06297","title":"Improving Sequential Query Recommendation with Immediate User Feedback","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2211.04586","title":"Learning to Price Supply Chain Contracts against a Learning Retailer","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2402.07067","title":"Learning the Expected Core of Strictly Convex Stochastic Cooperative Games","created":"2024-02-10","cited_by_count":0,"area":null},{"id":"2502.07397","title":"Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2502.14790","title":"Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2505.19061","title":"Hierarchical Adversarial Bandits for Online Configuration Optimization","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2505.24692","title":"Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.15966","title":"Vector preference-based contextual bandits under distributional shifts","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2605.29748","title":"Instance-dependent Stochastic Lipschitz bandit","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.23414","title":"Leveraging Similarities in Multi-Armed Bandits","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.10571","title":"Learning from Local Walks on Dynamic Graphs with Bandit Feedback","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.20258","title":"Breaking the $T^{3/4}$ Barrier for Regret Minimization With Bi-Dimensional CDFs","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.15036","title":"Lipschitz Bandits with Arbitrary Feedback Delays","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}