In recent years residual neural networks (ResNets) as introduced by [He, K., Zhang, X., Ren, S., and Sun, J., Proceedings of the IEEE conference on computer vision and pattern recognition (2016), 770-778] have become very popular in a large number of applications, including in image classification and segmentation. They provide a new perspective in training very deep neural networks without suffering the vanishing gradient problem. In this article we show that ResNets are able to approximate solutions of Kolmogorov partial differential equations (PDEs) with constant diffusion and possibly nonlinear drift coefficients without suffering the curse of dimensionality, which is to say the number of parameters of the approximating ResNets grows at most polynomially in the reciprocal of the approximation accuracy $\varepsilon > 0$ and the dimension of the considered PDE $d\in\mathbb{N}$. We adapt a proof in [Jentzen, A., Salimova, D., and Welti, T., Commun. Math. Sci. 19, 5 (2021), 1167-1205] - who showed a similar result for feedforward neural networks (FNNs) - to ResNets. In contrast to FNNs, the Euler-Maruyama approximation structure of ResNets simplifies the construction of the approximating ResNets substantially. Moreover, contrary to the above work, in our proof using ResNets does not require the existence of an FNN (or a ResNet) representing the identity map, which enlarges the set of applicable activation functions.
翻译:近年来,[He, K., Zhang, X., Ren, S.和Sun, J., J., 《IEEE关于计算机视觉和模式识别的会议记录》(2016年), 770-778) 推出的残余神经网络(ResNets)近年来在大量应用中变得非常受欢迎,包括在图像分类和分割方面。这些网络为培训非常深的神经网络提供了一种新的视角,而不会受到渐渐消失的梯度问题的影响。 在文章中,我们显示ResNets能够以不断的传播和可能的非线性漂移系数来接近 Kolmogorov部分差异方程式(PDEs)的解决方案,而不会受到维度的诅咒。 也就是说,在近似精度 $\varepslslslus > 0, 和所考虑的PDE $d\ in\ mathbb{N.