On the Spectral Bias of Deep Neural Networks

Nasim Rahaman, Devansh Arpit, Aristide Baratin, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, Aaron Courville

Published 2018-06-22Version 1

It is well known that over-parametrized deep neural networks (DNNs) are an overly expressive class of functions that can memorize even random data with $100\%$ training accuracy. This raises the question why they do not easily overfit real data. To answer this question, we study deep networks using Fourier analysis. We show that deep networks with finite weights (or trained for finite number of steps) are inherently biased towards representing smooth functions over the input space. Specifically, the magnitude of a particular frequency component ($k$) of deep ReLU network function decays at least as fast as $\mathcal{O}(k^{-2})$, with width and depth helping polynomially and exponentially (respectively) in modeling higher frequencies. This shows for instance why DNNs cannot perfectly \textit{memorize} peaky delta-like functions. We also show that DNNs can exploit the geometry of low dimensional data manifolds to approximate complex functions that exist along the manifold with simple functions when seen with respect to the input space. As a consequence, we find that all samples (including adversarial samples) classified by a network to belong to a certain class are connected by a path such that the prediction of the network along that path does not change. Finally we find that DNN parameters corresponding to functions with higher frequency components occupy a smaller volume in the parameter.