555 citations · 2.5k across the 105 of their papers we have counts for
Showing 2018 · cs.LGShow all
3 papers · 2 filters
cs.LG2018★ 28 cited
Escaping Saddle Points in Constrained Optimization
Aryan Mokhtari, Asuman Ozdaglar, Ali Jadbabaie
In this paper, we study the problem of escaping from saddle points in smooth nonconvex optimization problems subject to a convex set . We propose a generic framework t…
cs.LG2018★ 50 cited
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require hidden nodes to memorize/interpolate arbitrary data points. In contra…
cs.LG2018★ 26 cited
Small nonlinearities in activation functions create bad local minima in neural networks
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We investigate the loss surface of neural networks. We prove that even for one-hidden-layer networks with "slightest" nonlinearity, the empirical risks have spurious local minima i…