{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"2003.02395","title":"A Simple Convergence Proof of Adam and Adagrad","created":"2020-03-05","cited_by_count":171},{"id":"1810.10815","title":"Adaptive Online Learning in Dynamic Environments","created":"2018-10-25","cited_by_count":133},{"id":"1811.09358","title":"A Sufficient Condition for Convergences of Adam and RMSProp","created":"2018-11-23","cited_by_count":126},{"id":"2208.09632","title":"Adam Can Converge Without Any Modification On Update Rules","created":"2022-08-20","cited_by_count":114},{"id":"1502.07073","title":"Strongly Adaptive Online Learning","created":"2015-02-25","cited_by_count":107},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99},{"id":"1402.2044","title":"A Second-order Bound with Excess Losses","created":"2014-02-10","cited_by_count":95},{"id":"1601.01974","title":"Scale-Free Online Learning","created":"2016-01-08","cited_by_count":85},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81},{"id":"2112.14368","title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","created":"2021-12-29","cited_by_count":66},{"id":"1301.6677","title":"Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributions","created":"2013-01-23","cited_by_count":60},{"id":"2102.01046","title":"Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications","created":"2021-02-01","cited_by_count":52},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50},{"id":"2203.00444","title":"Parameter-free Mirror Descent","created":"2022-02-26","cited_by_count":45},{"id":"2302.03775","title":"Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion","created":"2023-02-07","cited_by_count":45},{"id":"1301.1254","title":"Dynamical Models and Tracking Regret in Online Convex Programming","created":"2013-01-07","cited_by_count":43},{"id":"1803.09349","title":"Logistic Regression: The Importance of Being Improper","created":"2018-03-25","cited_by_count":41},{"id":"1907.12340","title":"Bandit Convex Optimization in Non-stationary Environments","created":"2019-07-29","cited_by_count":41},{"id":"2104.11824","title":"Optimal Dynamic Regret in Exp-Concave Online Learning","created":"2021-04-23","cited_by_count":40},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40},{"id":"2112.06969","title":"A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions","created":"2021-12-13","cited_by_count":39},{"id":"2310.17998","title":"Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity","created":"2023-10-27","cited_by_count":38},{"id":"2201.12736","title":"No-Regret Learning in Time-Varying Zero-Sum Games","created":"2022-01-30","cited_by_count":36},{"id":"2003.09729","title":"A new regret analysis for Adam-type algorithms","created":"2020-03-21","cited_by_count":35},{"id":"2006.05876","title":"Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functions","created":"2020-06-10","cited_by_count":33},{"id":"1405.3843","title":"Logistic Regression: Tight Bounds for Stochastic and Online Optimization","created":"2014-05-15","cited_by_count":31},{"id":"2112.09002","title":"On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions","created":"2021-12-16","cited_by_count":31},{"id":"2201.08905","title":"Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond","created":"2022-01-21","cited_by_count":28},{"id":"2207.02121","title":"Adapting to Online Label Shift with Provable Guarantees","created":"2022-07-05","cited_by_count":26},{"id":"2302.08300","title":"Deterministic Nonsmooth Nonconvex Optimization","created":"2023-02-16","cited_by_count":26},{"id":"2402.01567","title":"Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise","created":"2024-02-02","cited_by_count":26},{"id":"1810.00143","title":"AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods","created":"2018-09-29","cited_by_count":24},{"id":"2405.18199","title":"Adam with model exponential moving average is effective for nonconvex optimization","created":"2024-05-28","cited_by_count":23},{"id":"2305.03938","title":"Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees","created":"2023-05-06","cited_by_count":22},{"id":"2405.09742","title":"Random Scaling and Momentum for Non-smooth Non-convex Optimization","created":"2024-05-16","cited_by_count":19},{"id":"2003.08109","title":"Efficient improper learning for online logistic regression","created":"2020-03-18","cited_by_count":16},{"id":"2202.02765","title":"Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States","created":"2022-02-06","cited_by_count":15},{"id":"2309.08911","title":"Efficient Methods for Non-stationary Online Learning","created":"2023-09-16","cited_by_count":15},{"id":"1711.02545","title":"Online Learning for Changing Environments using Coin Betting","created":"2017-11-06","cited_by_count":13},{"id":"2202.05630","title":"Scale-free Unconstrained Online Learning for Curved Losses","created":"2022-02-11","cited_by_count":13},{"id":"2209.13932","title":"Efficient and Near-Optimal Online Portfolio Selection","created":"2022-09-28","cited_by_count":13},{"id":"1909.03118","title":"Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyond","created":"2019-09-06","cited_by_count":12},{"id":"2402.02720","title":"Discounted Adaptive Online Learning: Towards Better Regularization","created":"2024-02-05","cited_by_count":12},{"id":"2408.09074","title":"Gradient-Variation Online Learning under Generalized Smoothness","created":"2024-08-17","cited_by_count":11},{"id":"2110.03020","title":"Efficient Methods for Online Multiclass Logistic Regression","created":"2021-10-06","cited_by_count":10},{"id":"2211.01357","title":"Quasi-Newton Steps for Efficient Online Exp-Concave Optimization","created":"2022-11-02","cited_by_count":10},{"id":"2405.19175","title":"Online Linear Regression in Dynamic Environments via Discounting","created":"2024-05-29","cited_by_count":10},{"id":"2202.07574","title":"Damped Online Newton Step for Portfolio Selection","created":"2022-02-15","cited_by_count":9},{"id":"2406.01577","title":"An Equivalence Between Static and Dynamic Regret Minimization","created":"2024-06-03","cited_by_count":9},{"id":"2506.10616","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","created":"2025-06-12","cited_by_count":7},{"id":"2209.12463","title":"On the Complexity of Deterministic Nonsmooth and Nonconvex Optimization","created":"2022-09-26","cited_by_count":6},{"id":"2302.08652","title":"Minimizing Dynamic Regret on Geodesic Metric Spaces","created":"2023-02-17","cited_by_count":6},{"id":"2411.03107","title":"Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs","created":"2024-11-05","cited_by_count":5},{"id":"2505.22899","title":"On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning","created":"2025-05-28","cited_by_count":5},{"id":"2507.05478","title":"Dynamic Regret Reduces to Kernelized Static Regret","created":"2025-07-07","cited_by_count":5},{"id":"2511.02773","title":"Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold","created":"2025-11-04","cited_by_count":5},{"id":"2505.19491","title":"Discounted Online Convex Optimization: Uniform Regret Across a Continuous Interval","created":"2025-05-26","cited_by_count":2},{"id":"2510.03478","title":"How to Set $\\beta_1, \\beta_2$ in Adam: An Online Learning Perspective","created":"2025-10-03","cited_by_count":2}],"next_cursor":null}