{"total":61,"rows":[{"id":"2206.00873","title":"Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs","created":"2022-06-02","cited_by_count":26,"area":null},{"id":"2206.00557","title":"A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs","created":"2022-06-01","cited_by_count":17,"area":null},{"id":"2310.12370","title":"No-Regret Learning in Bilateral Trade via Global Budget Balance","created":"2023-10-18","cited_by_count":17,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2210.06846","title":"An $\\alpha$-regret analysis of Adversarial Bilateral Trade","created":"2022-10-13","cited_by_count":16,"area":null},{"id":"2302.10805","title":"Repeated Bilateral Trade Against a Smoothed Adversary","created":"2023-02-21","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":"2105.14260","title":"Understanding Bandits with Graph Feedback","created":"2021-05-29","cited_by_count":14,"area":null},{"id":"2106.03596","title":"Beyond Bandit Feedback in Online Multiclass Classification","created":"2021-06-07","cited_by_count":14,"area":null},{"id":"2210.04229","title":"Learning on the Edge: Online Learning with Stochastic Feedback Graphs","created":"2022-10-09","cited_by_count":12,"area":null},{"id":"2202.11795","title":"Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2302.08631","title":"Practical Contextual Bandits with Feedback Graphs","created":"2023-02-17","cited_by_count":11,"area":null},{"id":"2403.00715","title":"Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2305.15383","title":"On the Minimax Regret for Online Learning with Feedback Graphs","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2305.19036","title":"Delayed Bandits: When Do Intermediate Observations Help?","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2410.21547","title":"Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2311.02715","title":"Exploiting Correlated Auxiliary Feedback in Parameterized Bandits","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2107.02274","title":"Dueling Bandits with Adversarial Sleeping","created":"2021-07-05","cited_by_count":5,"area":null},{"id":"2202.06694","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2210.01376","title":"Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2306.02971","title":"Online Learning with Feedback Graphs: The True Shape of Regret","created":"2023-06-05","cited_by_count":5,"area":null},{"id":"2306.07098","title":"Efficiently Learning the Graph for Semi-supervised Learning","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2402.18591","title":"Stochastic contextual bandits with graph feedback: from independence number to MAS number","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2503.07555","title":"Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2106.04982","title":"Cooperative Online Learning with Feedback Graphs","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2107.09572","title":"Best-of-All-Worlds Bounds for Online Learning with Feedback Graphs","created":"2021-07-20","cited_by_count":4,"area":null},{"id":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2302.11700","title":"New Guarantees for Learning Revenue Maximizing Menus of Lotteries and Two-Part Tariffs","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2307.07264","title":"On Interpolating Experts and Multi-Armed Bandits","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2206.10022","title":"Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2406.16802","title":"Improved Regret Bounds for Bandits with Expert Advice","created":"2024-06-24","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":"2506.20898","title":"Multi-model Online Conformal Prediction with Graph-Structured Feedback","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2607.09015","title":"Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing","created":"2026-07-10","cited_by_count":3,"area":null},{"id":"2102.04690","title":"Graph-Aided Online Multi-Kernel Learning","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2106.08441","title":"Online Learning with Uncertain Feedback Graphs","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2202.13447","title":"Graph-Assisted Communication-Efficient Ensemble Federated Learning","created":"2022-02-27","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":"2501.10181","title":"Improved learning rates in multi-unit uniform price auctions","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2510.16811","title":"Graph Learning Is Suboptimal in Causal Bandits","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2205.15076","title":"Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition","created":"2022-05-30","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":"2308.15107","title":"Stochastic Graph Bandit Learning with Side-Observations","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2402.15127","title":"Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2502.18826","title":"Adversarial Combinatorial Semi-bandits with Graph Feedback","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2510.19158","title":"Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.00461","title":"Laplacian Kernelized Bandit","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2603.08558","title":"Impact of Connectivity on Laplacian Representations in Reinforcement Learning","created":"2026-03-09","cited_by_count":1,"area":"deeprl"},{"id":"2207.04054","title":"Online Learning in Supply-Chain Games","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","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":"2502.07514","title":"A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond","created":"2025-02-11","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":"2508.14311","title":"Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2601.01692","title":"Enhanced Multi-model Online Conformal Prediction","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.07273","title":"Hybrid Feedback-Guided Optimal Learning for Wireless Interactive Panoramic Scene Delivery","created":"2026-02-06","cited_by_count":0,"area":null},{"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":"2607.10571","title":"Learning from Local Walks on Dynamic Graphs with Bandit Feedback","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.11873","title":"DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}