{"total":19,"rows":[{"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":"2408.09966","title":"Mask in the Mirror: Implicit Sparsification","created":"2024-08-19","cited_by_count":14,"area":null},{"id":"2107.01906","title":"The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities","created":"2021-07-05","cited_by_count":12,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2504.12883","title":"Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?","created":"2025-04-17","cited_by_count":12,"area":null},{"id":"2311.02374","title":"Riemannian stochastic optimization methods avoid strict saddle points","created":"2023-11-04","cited_by_count":8,"area":null},{"id":"2306.14522","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","created":"2023-06-26","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":"2101.00935","title":"First-Order Methods for Convex Optimization","created":"2021-01-04","cited_by_count":4,"area":null},{"id":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2507.15264","title":"On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem","created":"2025-07-21","cited_by_count":3,"area":null},{"id":"2412.16765","title":"Optimization Insights into Deep Diagonal Linear Networks","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2506.13286","title":"The impact of uncertainty on regularized learning in games","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2509.04008","title":"Towards understanding Accelerated Stein Variational Gradient Flow -- Analysis of Generalized Bilinear Kernels for Gaussian target distributions","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2608.01658","title":"Non-KKT Accumulation in Entropic Mirror Descent","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2207.04934","title":"Multilevel Geometric Optimization for Regularised Constrained Linear Inverse Problems","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2505.10272","title":"Spike-timing-dependent Hebbian learning as noisy gradient descent","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2608.07248","title":"Establishing Boundary KKT Convergence of Mirror Descent through Reparameterization","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2610.16868","title":"From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}