Document Type
Conference Proceeding
Publication Date
2018
Abstract
We study the loss surface of neural networks equipped with a hinge loss criterion and ReLU or leaky ReLU nonlinearities. Any such network defines a piecewise multilinear form in parameter space. By appealing to harmonic analysis we show that all local minima of such network are non-differentiable, except for those minima that occur in a region of parameter space where the loss surface is perfectly flat. Non-differentiable minima are therefore not technicalities or pathologies; they are heart of the problem when investigating the loss of ReLU networks. As a consequence, we must employ techniques from nonsmooth analysis to study these loss surfaces. We show how to apply these techniques in some illustrative cases.
Original Publication Citation
Laurent, T. & Brecht, J.. (2018). The Multilinear Structure of ReLU Networks. Proceedings of the 35th International Conference on Machine Learning, in PMLR 80:2908-2916
Digital Commons @ LMU & LLS Citation
Laurent, Thomas, "The Multilinear Structure of ReLU Networks" (2018). Mathematics, Statistics and Data Science Faculty Works. 120.
https://digitalcommons.lmu.edu/math_fac/120
Supplementary PDF