{"total":77,"rows":[{"id":"2302.09739","title":"A Blackbox Approach to Best of Both Worlds in Bandits and Beyond","created":"2023-02-20","cited_by_count":30,"area":null},{"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":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2207.14550","title":"Best-of-Both-Worlds Algorithms for Partial Monitoring","created":"2022-07-29","cited_by_count":19,"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":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","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":"2305.17301","title":"Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds","created":"2023-05-26","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":"2406.11316","title":"Improved Algorithms for Contextual Dynamic Pricing","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2110.14243","title":"Online Selective Classification with Limited Feedback","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2310.11558","title":"Online Algorithms with Uncertainty-Quantified Predictions","created":"2023-10-17","cited_by_count":9,"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":"2306.06247","title":"Online Learning with Set-Valued Feedback","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2311.02715","title":"Exploiting Correlated Auxiliary Feedback in Parameterized Bandits","created":"2023-11-05","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":"2206.07908","title":"Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","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":"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":"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":"2307.07264","title":"On Interpolating Experts and Multi-Armed Bandits","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2310.19064","title":"Apple Tasting: Combinatorial Dimensions and Minimax Rates","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2402.10282","title":"Information Capacity Regret Bounds for Bandits with Mediator Feedback","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2410.10404","title":"Deterministic Apple Tasting","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2503.07824","title":"Pure Exploration with Feedback Graphs","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2604.13740","title":"Online learning with noisy side observations","created":"2026-04-15","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":"2405.20028","title":"A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds","created":"2024-05-30","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":"2407.00571","title":"Adversarial Online Learning with Temporal Feedback Graphs","created":"2024-06-30","cited_by_count":3,"area":null},{"id":"2510.23992","title":"Optimal Arm Elimination Algorithms for Combinatorial Bandits","created":"2025-10-28","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":"2106.08441","title":"Online Learning with Uncertain Feedback Graphs","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2412.06079","title":"Learning from Snapshots of Discrete and Continuous Data Streams","created":"2024-12-08","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","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":"2605.00489","title":"Revealing graph bandits for maximizing local influence","created":"2026-05-01","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":"2308.08046","title":"Regret Lower Bounds in Multi-agent Multi-armed Bandit","created":"2023-08-15","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":"2401.10478","title":"Budgeted Online Model Selection and Fine-Tuning via Federated Learning","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2502.04678","title":"Nearly Tight Bounds for Cross-Learning Contextual Bandits with Graphical Feedback","created":"2025-02-07","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":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2505.23720","title":"COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents","created":"2025-05-29","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":"2511.05802","title":"Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2604.25271","title":"Online learning with Erd\\H{o}s-R\\'enyi side-observation graphs","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.29645","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2106.08187","title":"Thompson Sampling for Unimodal Bandits","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2409.05980","title":"Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2505.10698","title":"Asymptotically-Optimal Gaussian Bandits with Side Observations","created":"2025-05-15","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":"2601.03629","title":"Learning Shortest Paths When Data is Scarce","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.03175","title":"Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedback","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.04247","title":"Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback","created":"2026-03-04","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":"2605.22438","title":"Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.03851","title":"Two-Action Apple Tasting with Switching Costs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.09030","title":"Closing the loop in learning with missing data","created":"2026-08-10","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},{"id":"2608.16216","title":"Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.01761","title":"Pooling and Drift in Delayed Bandits","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.14790","title":"Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}