{"total":153,"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":"2201.12736","title":"No-Regret Learning in Time-Varying Zero-Sum Games","created":"2022-01-30","cited_by_count":36,"area":null},{"id":"2108.08843","title":"Learning Equilibria in Matching Markets from Bandit Feedback","created":"2021-08-19","cited_by_count":34,"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":"2208.09407","title":"Learning in Stackelberg Games with Non-myopic Agents","created":"2022-08-19","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":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"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":"2108.13298","title":"E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modeling","created":"2021-08-11","cited_by_count":21,"area":null},{"id":"2208.13663","title":"Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning","created":"2022-08-29","cited_by_count":21,"area":null},{"id":"2301.13306","title":"Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2102.08754","title":"A Regret Analysis of Bilateral Trade","created":"2021-02-16","cited_by_count":19,"area":null},{"id":"2111.06537","title":"Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs","created":"2021-11-12","cited_by_count":18,"area":null},{"id":"2208.13713","title":"Online Bidding Algorithms for Return-on-Spend Constrained Advertisers","created":"2022-08-29","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":"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":"2402.16710","title":"Cost Aware Best Arm Identification","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","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":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2205.14572","title":"No-regret Learning in Repeated First-Price Auctions with Budget Constraints","created":"2022-05-29","cited_by_count":9,"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":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2202.03704","title":"Budgeted Combinatorial Multi-Armed Bandits","created":"2022-02-08","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":"2304.05219","title":"BanditQ: Fair Bandits with Guaranteed Rewards","created":"2023-04-11","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":"2306.07071","title":"Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals","created":"2023-06-12","cited_by_count":6,"area":null},{"id":"2306.08470","title":"Bandits with Replenishable Knapsacks: the Best of both Worlds","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2311.05511","title":"Anytime-Constrained Reinforcement Learning","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2310.06306","title":"Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing","created":"2023-10-10","cited_by_count":5,"area":null},{"id":"2312.12794","title":"Bandit Sequential Posted Pricing via Half-Concavity","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2409.20489","title":"Online Decision Deferral under Budget Constraints","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2411.13993","title":"Market Making without Regret","created":"2024-11-21","cited_by_count":5,"area":null},{"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":"2104.05781","title":"Censored Semi-Bandits for Resource Allocation","created":"2021-04-12","cited_by_count":4,"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":"2206.03019","title":"The Survival Bandit Problem","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2501.18049","title":"Online Pricing and Allocation with Demand Learning and Fulfillment Cost","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2502.06168","title":"Dynamic Pricing with Adversarially-Censored Demands","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2604.00136","title":"ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving","created":"2026-03-31","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":"2201.07139","title":"Safe Online Bid Optimization with Return on Investment and Budget Constraints","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2206.00314","title":"Contextual Bandits with Knapsacks for a Conversion Model","created":"2022-06-01","cited_by_count":3,"area":null},{"id":"2207.11159","title":"Network Revenue Management with Demand Learning and Fair Resource-Consumption Balancing","created":"2022-07-22","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":"2409.05798","title":"Enhancing Preference-based Linear Bandits via Human Response Time","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2501.07022","title":"Improved Regret Bounds for Online Fair Division with Bandit Learning","created":"2025-01-13","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":"2505.02963","title":"Single-Sample and Robust Online Resource Allocation","created":"2025-05-05","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":"2509.25777","title":"Online Decision Making with Generative Action Sets","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2608.04333","title":"Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2102.00321","title":"Recurrent Submodular Welfare and Matroid Blocking Bandits","created":"2021-01-30","cited_by_count":2,"area":null},{"id":"2103.05199","title":"Dynamic Pricing and Learning under the Bass Model","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2106.01135","title":"MNL-Bandit with Knapsacks: a near-optimal algorithm","created":"2021-06-02","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":"2305.15807","title":"Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2306.13440","title":"Trading-off price for data quality to achieve fair online allocation","created":"2023-06-23","cited_by_count":2,"area":null},{"id":"2404.04467","title":"Demand Balancing in Primal-Dual Optimization for Blind Network Revenue Management","created":"2024-04-06","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":"2502.11673","title":"Best of Both Worlds: Regret Minimization versus Minimax Play","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.03195","title":"Online Bidding under RoS Constraints without Knowing the Value","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2507.04438","title":"Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities","created":"2025-07-06","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":"2602.14580","title":"Replicable Constrained Bandits","created":"2026-02-16","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":"2110.05724","title":"Query-Reward Tradeoffs in Multi-Armed Bandits","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","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":"2303.11522","title":"Online Learning for Equilibrium Pricing in Markets under Incomplete Information","created":"2023-03-21","cited_by_count":1,"area":null},{"id":"2307.05698","title":"Online Ad Procurement in Non-stationary Autobidding Worlds","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2307.12915","title":"Consensus-based Participatory Budgeting for Legitimacy: Decision Support via Multi-agent Reinforcement Learning","created":"2023-07-24","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":"2405.04910","title":"Learning with Posterior Sampling for Revenue Management under Time-varying Demand","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2407.05564","title":"A Re-solving Heuristic for Dynamic Assortment Optimization with Knapsack Constraints","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2408.07831","title":"Learning-Augmented Competitive Algorithms for Spatiotemporal Online Allocation with Deadline Constraints","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2408.15535","title":"Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2504.20908","title":"MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.02640","title":"Adaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2505.05169","title":"Bandit Max-Min Fair Allocation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null}],"next_cursor":"100"}