activity
20142026
most citedSimple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization

8 citations · 17 across the 18 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

math.OC2022

Perturbed Iterate SGD for Lipschitz Continuous Loss Functions with Numerical Error and Adaptive Step Sizes

Michael R. Metel

Motivated by neural network training in finite-precision arithmetic environments, this work studies the convergence of perturbed iterate SGD using adaptive step sizes in an environ…

math.OC2022

Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint

Michael R. Metel

This paper is motivated by structured sparsity for deep neural network training. We study a weighted group L0-norm constraint, and present the projection and normal cone of this se…