{"total":63,"rows":[{"id":"2106.12529","title":"Who Leads and Who Follows in Strategic Classification?","created":"2021-06-23","cited_by_count":53,"area":null},{"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":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"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":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"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":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2103.04546","title":"Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games","created":"2021-03-08","cited_by_count":15,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2112.02856","title":"Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback","created":"2021-12-06","cited_by_count":15,"area":null},{"id":"2103.04539","title":"Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games","created":"2021-03-08","cited_by_count":12,"area":null},{"id":"2103.04550","title":"No Weighted-Regret Learning in Adversarial Bandits with Delays","created":"2021-03-08","cited_by_count":12,"area":null},{"id":"2406.06506","title":"Online Newton Method for Bandit Convex Optimisation","created":"2024-06-10","cited_by_count":12,"area":null},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2210.05584","title":"On Adaptivity in Non-stationary Stochastic Optimization With Bandit Feedback","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2102.00490","title":"Online Markov Decision Processes with Aggregate Bandit Feedback","created":"2021-01-31","cited_by_count":10,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","cited_by_count":10,"area":null},{"id":"2302.05371","title":"A Second-Order Method for Stochastic Bandit Convex Optimisation","created":"2023-02-10","cited_by_count":10,"area":null},{"id":"2206.03362","title":"Building Robust Ensembles via Margin Boosting","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2402.09152","title":"Improved Regret for Bandit Convex Optimization with Delayed Feedback","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2205.13910","title":"A gradient estimator via L1-randomization for online zero-order optimization with two point feedback","created":"2022-05-27","cited_by_count":7,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2506.10616","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2109.05829","title":"Zeroth-order non-convex learning via hierarchical dual averaging","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2210.09903","title":"Online Convex Optimization with Unbounded Memory","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2310.14085","title":"Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback","created":"2023-10-21","cited_by_count":6,"area":null},{"id":"2304.02693","title":"A Certified Radius-Guided Attack Framework to Image Segmentation Models","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2102.07387","title":"Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization","created":"2021-02-15","cited_by_count":3,"area":null},{"id":"2106.00444","title":"Minimax Regret for Bandit Convex Optimisation of Ridge Functions","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2202.06150","title":"Adaptive Bandit Convex Optimization with Heterogeneous Curvature","created":"2022-02-12","cited_by_count":2,"area":null},{"id":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2208.06720","title":"A Near-Optimal Algorithm for Univariate Zeroth-Order Budget Convex Optimization","created":"2022-08-13","cited_by_count":2,"area":null},{"id":"2210.05618","title":"Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2306.12383","title":"Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2311.02423","title":"Payoff-based learning with matrix multiplicative weights in quantum games","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","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":"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":"2103.16082","title":"Optimal Stochastic Nonconvex Optimization with Bandit Feedback","created":"2021-03-30","cited_by_count":1,"area":null},{"id":"2204.12764","title":"Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2401.09278","title":"Adaptive Regret for Bandits Made Possible: Two Queries Suffice","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2406.18672","title":"A simple and improved algorithm for noisy, convex, zeroth-order optimisation","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2406.19617","title":"Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2410.05942","title":"Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2503.10836","title":"Exploiting Concavity Information in Gaussian Process Contextual Bandit Optimization","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.02980","title":"Non-stationary Bandit Convex Optimization: A Comprehensive Study","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2601.00461","title":"Laplacian Kernelized Bandit","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2605.22191","title":"Bandit Convex Optimization with Gradient Prediction Adaptivity","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.18652","title":"The Price of Hidden Curvature: Improved Lower Bounds for Bandit Convex Optimization","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2111.05486","title":"Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2111.13026","title":"Bandit problems with fidelity rewards","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2208.01185","title":"A Note on Zeroth-Order Optimization on the Simplex","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2210.05222","title":"Stochastic Direct Search Method for Blind Resource Allocation","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2302.00358","title":"Bandit Convex Optimisation Revisited: FTRL Achieves $\\tilde{O}(t^{1/2})$ Regret","created":"2023-02-01","cited_by_count":0,"area":null},{"id":"2403.01361","title":"Bandit Profit-maximization for Targeted Marketing","created":"2024-03-03","cited_by_count":0,"area":null},{"id":"2404.17158","title":"Online $\\mathrm{L}^{\\natural}$-Convex Minimization","created":"2024-04-26","cited_by_count":0,"area":null},{"id":"2406.05714","title":"A conversion theorem and minimax optimality for continuum contextual bandits","created":"2024-06-09","cited_by_count":0,"area":null},{"id":"2501.11127","title":"A Regularized Online Newton Method for Stochastic Convex Bandits with Linear Vanishing Noise","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2505.07303","title":"Online Episodic Convex Reinforcement Learning","created":"2025-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.19891","title":"Adversarial Bandit Optimization with Globally Bounded Perturbations to Convex Losses","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.12938","title":"Sharp Optimal Algorithm for Derivative-Free Stochastic Convex Optimization in One Dimension","created":"2026-07-14","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}],"next_cursor":null}