Convergence of stochastic gradient descent for learning linear neural networks

Paper recorded by Signals 4 on 2026-10-20 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-20 on arXiv · recorded by Signals 4 on 2026-10-21

Category: cs.LG · 机器学习 · first seen 2026-10-21

Abstract

Stochastic gradient descent (SGD) is the cornerstone of modern deep learning, yet its theoretical convergence properties remain poorly understood in non-convex settings. To address this gap, we study SGD dynamics in deep linear neural networks - simplified models that retain key non-convex characteristics while remaining analytically tractable. Building on recent results for gradient descent, we e

Read on arXiv →