Pointwise convergence of Fourier series and deep neural network for the indicator function of d-dimensional ball

arXiv2304.08172MaRDI QIDQ6509680FDOQ6509680

Authors: Ryota Kawasumi, Tsuyoshi Yoneda 

Abstract: The theoretical structure of deep neural network (DNN) has been clarified gradually. Imaizumi-Fukumizu (2019) and Suzuki (2019) clarified that the learning ability of DNN is superior to the previous theories when the target function is non-smooth functions. However, as far as the author is aware, none of the numerous works to date attempted to mathematically investigate what kind of DNN architectures really induce pointwise convergence of gradient descent (without any statistical argument), and this attempt seems to be closer to the practical DNNs. In this paper we restrict target functions to non-smooth indicator functions, and construct a deep neural network inducing pointwise convergence provided by gradient descent process in ReLU-DNN. The DNN has a sparse and a special shape, with certain variable transformations.

This page was built for publication: Pointwise convergence of Fourier series and deep neural network for the indicator function of d-dimensional ball

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6509680)