{"total":95,"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":"2106.05135","title":"Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints","created":"2021-06-09","cited_by_count":39,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2305.00316","title":"The Ideal Continual Learner: An Agent That Never Forgets","created":"2023-04-29","cited_by_count":35,"area":null},{"id":"2310.18955","title":"Optimal Algorithms for Online Convex Optimization with Adversarial Constraints","created":"2023-10-29","cited_by_count":34,"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":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"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":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"id":"2105.00321","title":"Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization","created":"2021-05-01","cited_by_count":21,"area":null},{"id":"2108.09435","title":"Fairness-Aware Online Meta-learning","created":"2021-08-21","cited_by_count":19,"area":null},{"id":"2212.09513","title":"Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization","created":"2022-12-19","cited_by_count":19,"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":"2306.00149","title":"Distributed Online Convex Optimization with Adversarial Constraints: Reduced Cumulative Constraint Violation Bounds under Slater's Condition","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2502.00792","title":"RTBAgent: A LLM-based Agent System for Real-Time Bidding","created":"2025-02-02","cited_by_count":14,"area":"agents"},{"id":"2111.07430","title":"Safe Online Convex Optimization with Unknown Linear Safety Constraints","created":"2021-11-14","cited_by_count":13,"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":"2111.07707","title":"Simultaneously Achieving Sublinear Regret and Constraint Violations for Online Convex Optimization with Time-varying Constraints","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2306.01007","title":"Towards Fair Disentangled Online Learning for Changing Environments","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2501.19214","title":"A single-loop SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2209.11837","title":"Doubly Fair Dynamic Pricing","created":"2022-09-23","cited_by_count":8,"area":null},{"id":"2302.14796","title":"Particle-based Online Bayesian Sampling","created":"2023-02-28","cited_by_count":7,"area":null},{"id":"2103.11370","title":"Online Convex Optimization with Continuous Switching Constraint","created":"2021-03-21","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":"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":"2412.17018","title":"GAS: Generative Auto-bidding with Post-training Search","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2504.15243","title":"Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2106.11577","title":"Solving Stochastic Optimization with Expectation Constraints Efficiently by a Stochastic Augmented Lagrangian-Type Algorithm","created":"2021-06-22","cited_by_count":5,"area":null},{"id":"2202.07868","title":"Data-Driven Minimax Optimization with Expectation Constraints","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2206.04475","title":"Individually Fair Learning with One-Sided Feedback","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2302.01203","title":"Online Learning under Budget and ROI Constraints via Weak Adaptivity","created":"2023-02-02","cited_by_count":5,"area":null},{"id":"2302.02426","title":"Online Nonstochastic Control with Adversarial and Static Constraints","created":"2023-02-05","cited_by_count":5,"area":null},{"id":"2501.16046","title":"Revisiting Projection-Free Online Learning with Time-Varying Constraints","created":"2025-01-27","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":"2201.02890","title":"Lazy Lagrangians with Predictions for Online Learning","created":"2022-01-08","cited_by_count":4,"area":null},{"id":"2203.17150","title":"Online Learning for Traffic Routing under Unknown Preferences","created":"2022-03-31","cited_by_count":4,"area":null},{"id":"2209.04086","title":"Stochastic Compositional Optimization with Compositional Constraints","created":"2022-09-09","cited_by_count":4,"area":null},{"id":"2302.12320","title":"Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2510.01867","title":"Universal Dynamic Regret and Constraint Violation Bounds for Constrained Online Convex Optimization","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2605.07386","title":"Convex Optimization with Nested Evolving Feasible Sets","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2403.06812","title":"Monotone Individual Fairness","created":"2024-03-11","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":"2510.04685","title":"Parameter-free Algorithms for the Stochastically Extended Adversarial Model","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2603.20671","title":"Breaking the $O(\\sqrt{T})$ Cumulative Constraint Violation Barrier while Achieving $O(\\sqrt{T})$ Static Regret in Constrained Online Convex Optimization","created":"2026-03-21","cited_by_count":3,"area":null},{"id":"2105.04005","title":"Delay-Tolerant Constrained OCO with Application to Network Resource Allocation","created":"2021-05-09","cited_by_count":2,"area":null},{"id":"2205.00825","title":"Stochastic Online Fisher Markets: Static Pricing Limits and Adaptive Enhancements","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2210.16735","title":"Online Convex Optimization with Long Term Constraints for Predictable Sequences","created":"2022-10-30","cited_by_count":2,"area":null},{"id":"2305.01333","title":"Projection-Free Online Convex Optimization with Stochastic Constraints","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2412.10703","title":"Doubly-Bounded Queue for Constrained Online Learning: Keeping Pace with Dynamics of Both Loss and Constraint","created":"2024-12-14","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":"2505.12530","title":"Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.20010","title":"Data-Dependent Regret Bounds for Constrained MABs","created":"2025-05-26","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":"2603.27884","title":"Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards","created":"2026-03-29","cited_by_count":2,"area":"deeprl"},{"id":"2606.08028","title":"Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2606.31480","title":"Constrained Online Convex Optimization without Slater's Condition","created":"2026-06-30","cited_by_count":2,"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":"2303.11522","title":"Online Learning for Equilibrium Pricing in Markets under Incomplete Information","created":"2023-03-21","cited_by_count":1,"area":null},{"id":"2306.05046","title":"A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2306.14094","title":"Locally Differentially Private Distributed Online Learning with Guaranteed Optimality","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2403.05786","title":"Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2405.09296","title":"Tight Bounds for Online Convex Optimization with Adversarial Constraints","created":"2024-05-15","cited_by_count":1,"area":null},{"id":"2405.19015","title":"Distributed Management of Fluctuating Energy Resources in Dynamic Networked Systems","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2412.09594","title":"Wait-Less Offline Tuning and Re-solving for Online Decision Making","created":"2024-12-12","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},{"id":"2601.20257","title":"C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding","created":"2026-01-28","cited_by_count":1,"area":"offlinerl"},{"id":"2602.08261","title":"PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2204.02197","title":"Penalised FTRL With Time-Varying Constraints","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2205.09571","title":"Augmented Lagrangian Methods for Time-varying Constrained Online Convex Optimization","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2310.00962","title":"Multi-Agent Bayesian Optimization with Coupled Black-Box and Affine Constraints","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2311.02426","title":"Online Non-convex Optimization with Long-term Non-convex Constraints","created":"2023-11-04","cited_by_count":0,"area":null},{"id":"2311.11180","title":"Nonsmooth Projection-Free Optimization with Functional Constraints","created":"2023-11-18","cited_by_count":0,"area":null},{"id":"2412.03983","title":"Safe and Efficient Online Convex Optimization with Linear Budget Constraints and Partial Feedback","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2502.05599","title":"Online Bidding Algorithms with Strict Return on Spend (ROS) Constraint","created":"2025-02-08","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":"2509.05930","title":"Smoothed Online Optimization for Target Tracking: Robust and Learning-Augmented Algorithms","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2510.13560","title":"Multi-Objective $\\textit{min-max}$ Online Convex Optimization","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.05915","title":"CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computing","created":"2025-11-08","cited_by_count":0,"area":"rag"},{"id":"2601.02754","title":"Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies","created":"2026-01-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.14543","title":"Truly Adapting to Adversarial Constraints in Constrained MABs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.14319","title":"Structure-Dependent Regret and Constraint Violation Bounds for Online Convex Optimization with Time-Varying Constraints","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.11535","title":"Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.19457","title":"Generative Auto-Bidding with Unified Modeling and Exploration","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.27811","title":"Constrained Auto-Bidding via Generative Response Modeling","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.06017","title":"Learning When to Automate: Queue Control in Human-AI Service Systems","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.10808","title":"Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.17281","title":"AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization","created":"2026-07-19","cited_by_count":0,"area":"synth"},{"id":"2607.25233","title":"Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27626","title":"Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning","created":"2026-07-30","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},{"id":"2610.15011","title":"Conformal Sequential Decision Making With Cost and Sublinear Policy Regret Guarantees","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}