{"total":83,"rows":[{"id":"2209.07454","title":"A Unifying Framework for Online Optimization with Long-Term Constraints","created":"2022-09-15","cited_by_count":41,"area":null},{"id":"2211.07484","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","created":"2022-11-14","cited_by_count":30,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2109.12974","title":"Bilateral Trade: A Regret Minimization Perspective","created":"2021-09-08","cited_by_count":29,"area":null},{"id":"2103.10246","title":"Stochastic Bandits for Multi-platform Budget Optimization in Online Advertising","created":"2021-03-16","cited_by_count":25,"area":null},{"id":"2205.12427","title":"Non-stationary Bandits with Knapsacks","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2102.03192","title":"Provably Efficient Algorithms for Multi-Objective Competitive RL","created":"2021-02-05","cited_by_count":22,"area":null},{"id":"2102.08754","title":"A Regret Analysis of Bilateral Trade","created":"2021-02-16","cited_by_count":19,"area":null},{"id":"2102.06385","title":"The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks","created":"2021-02-12","cited_by_count":16,"area":null},{"id":"2204.00706","title":"Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk","created":"2022-04-01","cited_by_count":15,"area":null},{"id":"2209.13694","title":"Safe Linear Bandits over Unknown Polytopes","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2102.10156","title":"Learning to Persuade on the Fly: Robustness Against Ignorance","created":"2021-02-19","cited_by_count":12,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2206.07316","title":"Online Contextual Decision-Making with a Smart Predict-then-Optimize Method","created":"2022-06-15","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":"2210.11834","title":"Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2405.16118","title":"Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2404.09832","title":"No-Regret Algorithms in non-Truthful Auctions with Budget and ROI Constraints","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2104.09750","title":"Joint Online Learning and Decision-making via Dual Mirror Descent","created":"2021-04-20","cited_by_count":8,"area":null},{"id":"2203.15629","title":"Stochastic Conservative Contextual Linear Bandits","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2302.14686","title":"Approximately Stationary Bandits with Knapsacks","created":"2023-02-28","cited_by_count":6,"area":null},{"id":"2306.03655","title":"Online Learning under Adversarial Nonlinear Constraints","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2405.06575","title":"No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2407.01458","title":"Contractual Reinforcement Learning: Pulling Arms with Invisible Hands","created":"2024-07-01","cited_by_count":5,"area":"deeprl"},{"id":"2409.20489","title":"Online Decision Deferral under Budget Constraints","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2505.23436","title":"Emergent Risk Awareness in Rational Agents under Resource Constraints","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2506.13244","title":"No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2106.05165","title":"A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2202.13710","title":"Best of Many Worlds Guarantees for Online Learning with Knapsacks","created":"2022-02-28","cited_by_count":4,"area":null},{"id":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2402.11285","title":"Fair Resource Allocation in Virtualized O-RAN Platforms","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2102.04824","title":"A Multi-Arm Bandit Approach To Subset Selection Under Constraints","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2110.09133","title":"Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2205.05659","title":"Ranked Prioritization of Groups in Combinatorial Bandit Allocation","created":"2022-05-11","cited_by_count":3,"area":null},{"id":"2305.18511","title":"Contextual Bandits with Budgeted Information Reveal","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2311.01327","title":"High-dimensional Linear Bandits with Knapsacks","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2402.19090","title":"Best Arm Identification with Resource Constraints","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2406.15648","title":"Testing the Feasibility of Linear Programs with Bandit Feedback","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2503.14796","title":"A New Benchmark for Online Learning with Budget-Balancing Constraints","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","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":"2510.02820","title":"Online Learning in the Random Order Model","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2103.12833","title":"Online Learning in Budget-Constrained Dynamic Colonel Blotto Games","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2301.11267","title":"Online Convex Optimization with Stochastic Constraints: Zero Constraint Violation and Bandit Feedback","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2302.04182","title":"Online Resource Allocation: Bandits feedback and Advice on Time-varying Demands","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2312.09961","title":"Risk-Aware Continuous Control with Neural Contextual Bandits","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2401.01077","title":"Constrained Online Two-stage Stochastic Optimization: Algorithm with (and without) Predictions","created":"2024-01-02","cited_by_count":1,"area":null},{"id":"2507.06859","title":"Episodic Contextual Bandits with Knapsacks under Conversion Models","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2602.18114","title":"Non-Stationary Online Resource Allocation: Learning from a Single Sample","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2605.14241","title":"Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2606.15841","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2105.02589","title":"Bandit based centralized matching in two-sided markets for peer to peer lending","created":"2021-05-06","cited_by_count":0,"area":null},{"id":"2302.00997","title":"Constrained Online Two-stage Stochastic Optimization: Near Optimal Algorithms via Adversarial Learning","created":"2023-02-02","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":"2305.14537","title":"Disincentivizing Polarization in Social Networks","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.16578","title":"Allocating Divisible Resources on Arms with Unknown and Random Rewards","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.10722","title":"Clustered Linear Contextual Bandits with Knapsacks","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2310.14164","title":"$\\alpha$-Fair Contextual Bandits","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2407.00170","title":"Dataset Representativeness and Downstream Task Fairness","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2501.18560","title":"Bandits with Anytime Knapsacks","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2503.02043","title":"Constrained Linear Thompson Sampling","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.03499","title":"Optimistic Learning for Communication Networks","created":"2025-04-04","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":"2602.06565","title":"Learning to Allocate Resources with Censored Feedback","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.18431","title":"SMaRT: Online Reusable Resource Assignment and an Application to Mediation in the Kenyan Judiciary","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2602.24146","title":"Learning with a Budget: Identifying the Best Arm with Resource Constraints","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.06190","title":"Constrained Contextual Bandits with Adversarial Contexts","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.14953","title":"Efficient Online Conformal Selection with Limited Feedback","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.09623","title":"Constrained user-item allocation for e-commerce marketing campaigns","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.17489","title":"Online LLM Selection via Constrained Bandits with Time-Varying Demand","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.05620","title":"Safe Bayesian Optimization with Counterfactual Policies","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.10317","title":"Neutralizing Structural Inequality in the Nigerian FinTech Sector","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.13546","title":"From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.23432","title":"Experimentation and Commitment under Reward Shifts","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.11383","title":"Reoptimization Algorithms for Contextual Bandits with Knapsack Constraints","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.00710","title":"Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.06921","title":"Constrained Online Learning with Noisy Constraint Values","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}