{"total":43,"rows":[{"id":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2508.21141","title":"Adaptive LLM Routing under Budget Constraints","created":"2025-08-28","cited_by_count":24,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2207.03445","title":"Differentially Private Stochastic Linear Bandits: (Almost) for Free","created":"2022-07-07","cited_by_count":19,"area":null},{"id":"2102.01723","title":"Apollo: Transferable Architecture Exploration","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2111.06067","title":"Solving Multi-Arm Bandit Using a Few Bits of Communication","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2403.15640","title":"Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making","created":"2024-03-22","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2206.00099","title":"Provably and Practically Efficient Neural Contextual Bandits","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2402.04933","title":"Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits","created":"2024-02-07","cited_by_count":6,"area":null},{"id":"2106.15808","title":"Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2204.11910","title":"Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2105.14586","title":"Kolmogorov-Smirnov Test-Based Actively-Adaptive Thompson Sampling for Non-Stationary Bandits","created":"2021-05-30","cited_by_count":4,"area":null},{"id":"2106.13539","title":"Dealing with Expert Bias in Collective Decision-Making","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2202.05182","title":"Remote Contextual Bandits","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2103.15342","title":"A bandit-learning approach to multifidelity approximation","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2105.08869","title":"Incentivized Bandit Learning with Self-Reinforcing User Preferences","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2201.01628","title":"Bridging Adversarial and Nonstationary Multi-armed Bandit","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2207.06355","title":"Contextual Decision Trees","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","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":"2502.04021","title":"Variational Quantum Optimization with Continuous Bandits","created":"2025-02-06","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":"2109.13977","title":"Risk averse non-stationary multi-armed bandits","created":"2021-09-28","cited_by_count":1,"area":null},{"id":"2110.02388","title":"Fast and Interpretable Consensus Clustering via Minipatch Learning","created":"2021-10-05","cited_by_count":1,"area":null},{"id":"2205.09584","title":"Multi-Armed Bandits in Brain-Computer Interfaces","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2302.04989","title":"Causal Inference out of Control: Estimating the Steerability of Consumption","created":"2023-02-10","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":"2312.12400","title":"New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem","created":"2023-12-19","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":"2506.02386","title":"Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2101.00001","title":"Etat de l'art sur l'application des bandits multi-bras","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2206.10333","title":"Machine Learning Prescriptive Canvas for Optimizing Business Outcomes","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2410.16486","title":"Survival Multiarmed Bandits with Bootstrapping Methods","created":"2024-10-21","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":"2509.18739","title":"Consistency of Selection Strategies for Fraud Detection","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2602.05019","title":"A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.08558","title":"Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.26755","title":"Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.09929","title":"Expected Sample Complexity in Multi-Armed Bandits","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}