{"total":19,"rows":[{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110,"area":null},{"id":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2202.06915","title":"Stochastic linear optimization never overfits with quadratically-bounded losses on general data","created":"2022-02-14","cited_by_count":17,"area":null},{"id":"2105.13831","title":"Implicit Regularization in Matrix Sensing via Mirror Descent","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2205.07331","title":"Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent","created":"2022-05-15","cited_by_count":11,"area":null},{"id":"2202.11461","title":"Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition","created":"2022-02-23","cited_by_count":9,"area":null},{"id":"2202.13328","title":"Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization","created":"2022-02-27","cited_by_count":7,"area":null},{"id":"2106.05397","title":"From inexact optimization to learning via gradient concentration","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2202.09885","title":"On Optimal Early Stopping: Over-informative versus Under-informative Parametrization","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2202.06054","title":"Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2410.11227","title":"Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2412.16765","title":"Optimization Insights into Deep Diagonal Linear Networks","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2202.00420","title":"Iterative regularization for low complexity regularizers","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2205.00058","title":"Implicit Regularization Properties of Variance Reduced Stochastic Mirror Descent","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2603.20967","title":"Hard labels sampled from sparse targets mislead rotation invariant algorithms","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2201.08311","title":"Accelerated Gradient Flow: Risk, Stability, and Implicit Regularization","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2508.19028","title":"GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}