activity
20182020
most citedRobust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

17 citations · 21 across the 4 of their papers we have counts for

collaborators

5 papers

math.NA20203 cited

Monolithic Multigrid for Magnetohydrodynamics

J. H. Adler, T. Benson, E. C. Cyr +3

The magnetohydrodynamics (MHD) equations model a wide range of plasma physics applications and are characterized by a nonlinear system of partial differential equations that strong…

cs.LG2020

A block coordinate descent optimizer for classification problems exploiting convexity

Ravi G. Patel, Nathaniel A. Trask, Mamikon A. Gulian +1

Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as compared to gradient…

cs.LG20191 cited

Multilevel Initialization for Layer-Parallel Deep Neural Network Training

Eric C. Cyr, Stefanie Günther, Jacob B. Schroder

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous in…

cs.LG201917 cited

Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

Eric C. Cyr, Mamikon A. Gulian, Ravi G. Patel +2

Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of DNNs.…

math.OC2018

Layer-Parallel Training of Deep Residual Neural Networks

S. Günther, L. Ruthotto, J. B. Schroder +2

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification an…