A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
[article]
2017
arXiv
pre-print
Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization will succeed. Here we provide a strong result of this kind. We consider a neural net with one hidden layer and a convolutional structure with no overlap and a ReLU activation function. For this architecture we show that learning is NP-complete in the general
arXiv:1702.07966v1
fatcat:tzitjxzgxzfyldwetrqqy73kl4