{"total":18,"rows":[{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"area":null},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24,"area":null},{"id":"2205.01385","title":"Smooth over-parameterized solvers for non-smooth structured optimization","created":"2022-05-03","cited_by_count":11,"area":null},{"id":"2205.15235","title":"Non-convex online learning via algorithmic equivalence","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2210.06705","title":"From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2410.14158","title":"A Mirror Descent Perspective of Smoothed Sign Descent","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2503.08748","title":"Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2506.13984","title":"Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2212.12675","title":"Iterative regularization in classification via hinge loss diagonal descent","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2305.17275","title":"Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2310.17386","title":"A Challenge in Reweighting Data with Bilevel Optimization","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2510.12639","title":"Thermodynamic structure of the Sinkhorn flow","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2603.17527","title":"Mirror Descent on Riemannian Manifolds","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}