226 citations · 1.9k across the 128 of their papers we have counts for
3 papers · 2 filters
A Generic Approach for Escaping Saddle points
Sashank J Reddi, Manzil Zaheer, Suvrit Sra +4
A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly d…
Distributional Adversarial Networks
Chengtao Li, David Alvarez-Melis, Keyulu Xu +2
We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination. Inspired by discrepancy measure…
Global optimality conditions for deep neural networks
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, a…