Abstract | ||
---|---|---|
We study the loss surface of neural networks that involve only rectified linear unit (ReLU) nonlinearities from a theoretical point-of-view. Any such network defines a piecewise multilinear form in parameter space. As a consequence, optima of such networks generically occur in non-differentiable regions of parameter space and so any understanding of such networks must carefully take into account their non-smooth nature. We then proceed to leverage this multilinear structure in an analysis of a neural network with one hidden-layer. Under the assumption of linearly separable data, the piecewise bilinear structure of the loss allows us to provide an explicit description of all critical points. |
Year | Venue | DocType |
---|---|---|
2018 | ICML | Conference |
Volume | Citations | PageRank |
abs/1712.10132 | 3 | 0.39 |
References | Authors | |
14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurent, Thomas | 1 | 74 | 7.43 |
James H. von Brecht | 2 | 93 | 6.45 |