52 citations · 255 across the 21 of their papers we have counts for
Showing 2018Show all
3 papers · 1 filter
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…
math.OC2018★ 4 cited
Efficiently testing local optimality and escaping saddles for ReLU networks
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We provide a theoretical algorithm for checking local optimality and escaping saddles at nondifferentiable points of empirical risks of two-layer ReLU networks. Our algorithm recei…
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…