Smaller generalization error derived for a deep residual neural network compared to shallow networks


Abstract in English

Estimates of the generalization error are proved for a residual neural network with $L$ random Fourier features layers $bar z_{ell+1}=bar z_ell + mathrm{Re}sum_{k=1}^Kbar b_{ell k}e^{mathrm{i}omega_{ell k}bar z_ell}+ mathrm{Re}sum_{k=1}^Kbar c_{ell k}e^{mathrm{i}omega_{ell k}cdot x}$. An optimal distribution for the frequencies $(omega_{ell k},omega_{ell k})$ of the random Fourier features $e^{mathrm{i}omega_{ell k}bar z_ell}$ and $e^{mathrm{i}omega_{ell k}cdot x}$ is derived. This derivation is based on the corresponding generalization error for the approximation of the function values $f(x)$. The generalization error turns out to be smaller than the estimate ${|hat f|^2_{L^1(mathbb{R}^d)}}/{(KL)}$ of the generalization error for random Fourier features with one hidden layer and the same total number of nodes $KL$, in the case the $L^infty$-norm of $f$ is much less than the $L^1$-norm of its Fourier transform $hat f$. This understanding of an optimal distribution for random features is used to construct a new training method for a deep residual network. Promising performance of the proposed new algorithm is demonstrated in computational experiments.

Download