most citedA Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2022★ 2 cited

A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima

Taehee Ko, Xiantao Li

Loss functions with non-isolated minima have emerged in several machine learning problems, creating a gap between theory and practice. In this paper, we formulate a new type of loc…