{"total":13,"rows":[{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2106.04881","title":"Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms","created":"2021-06-09","cited_by_count":23,"area":null},{"id":"2307.06324","title":"Provably Faster Gradient Descent via Long Steps","created":"2023-07-12","cited_by_count":20,"area":null},{"id":"2310.01687","title":"From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression","created":"2023-10-02","cited_by_count":17,"area":null},{"id":"2209.13271","title":"The Curse of Unrolling: Rate of Differentiating Through Optimization","created":"2022-09-27","cited_by_count":16,"area":null},{"id":"2505.01423","title":"Negative Stepsizes Make Gradient-Descent-Ascent Converge","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2205.11361","title":"Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent","created":"2022-05-23","cited_by_count":9,"area":null},{"id":"2203.01400","title":"Adaptive Gradient Methods with Local Guarantees","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2207.02189","title":"Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2401.11600","title":"Understanding the Generalization Benefits of Late Learning Rate Decay","created":"2024-01-21","cited_by_count":6,"area":null},{"id":"2404.05782","title":"Dynamical stability and chaos in artificial neural network trajectories along training","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2608.10418","title":"A lower bound for stepsize-based acceleration of gradient descent","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2609.02855","title":"Improved Gradient Descent Lower Bounds Beyond Nesterov","created":"2026-09-02","cited_by_count":2,"area":null}],"next_cursor":null}