← Search

S. Jamaloddin Golestani

2 accepted papers

2020

Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU Networks

ICLR 2020poster

We study the landscape of squared loss in neural networks with one-hidden layer and ReLU activation functions. Let $m$ and $d$ be the widths of hidden and input layers, respectively. We show that there exist poor local minima with positive curvature for some training sets of size $n\geq m+2d-2$. By…

Cited by 10SourceScholar
2019

Order Optimal One-Shot Distributed Learning

NeurIPS 2019poster

We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d samples. Based on its observed samples, each machine then sends an $O(\log(mn))$-length message to a server, at which a parameter minimizing an expected loss is to be estimate…

Cited by 16SourcePDFScholar