{"total":23,"rows":[{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46,"area":null},{"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,"area":null},{"id":"2501.18965","title":"The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training","created":"2025-01-31","cited_by_count":33,"area":null},{"id":"2102.09393","title":"On the Convergence of Step Decay Step-Size for Stochastic Optimization","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2110.14109","title":"Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2502.11229","title":"Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2111.13526","title":"An Optimization Framework for Federated Edge Learning","created":"2021-11-26","cited_by_count":3,"area":null},{"id":"2505.23081","title":"Gradient Methods with Online Scaling Part I. Theoretical Foundations","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2106.02888","title":"Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization","created":"2021-06-05","cited_by_count":2,"area":null},{"id":"2201.10245","title":"On Uniform Boundedness Properties of SGD and its Momentum Variants","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2603.14514","title":"High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2401.06738","title":"(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2403.03180","title":"Shuffling Momentum Gradient Algorithm for Convex Optimization","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2406.05637","title":"A Generalized Version of Chung's Lemma and its Applications","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2412.16854","title":"Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2306.10278","title":"Adaptive Strategies in Non-convex Optimization","created":"2023-06-17","cited_by_count":0,"area":null},{"id":"2309.01248","title":"Modified Step Size for Enhanced Stochastic Gradient Descent: Convergence and Experiments","created":"2023-09-03","cited_by_count":0,"area":null},{"id":"2310.05692","title":"Based on What We Can Control Artificial Neural Networks","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2404.01257","title":"New logarithmic step size for stochastic gradient descent","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2503.09411","title":"Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2603.00023","title":"Riemannian Dueling Optimization","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.26316","title":"High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}