5 citations · 6 across the 2 of their papers we have counts for
3 papers
cs.LG2020
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Charles G. Frye, James Simon, Neha S. Wadia +3
Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from m…
math.OC2019★ 1 cited
Critical Point Finding with Newton-MR by Analogy to Computing Square Roots
Charles G Frye
Understanding of the behavior of algorithms for resolving the optimization problem (hereafter shortened to OP) of optimizing a differentiable loss function (OP1), is enhanced by kn…
cs.LG2019★ 5 cited
Numerically Recovering the Critical Points of a Deep Linear Autoencoder
Charles G. Frye, Neha S. Wadia, Michael R. DeWeese +1
Numerically locating the critical points of non-convex surfaces is a long-standing problem central to many fields. Recently, the loss surfaces of deep neural networks have been exp…