Optimal Approximation and Learning Rates for Deep Convolutional Neural Networks

Autor:	Lin, Shao-Bo
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Mathematics - Statistics Theory
Druh dokumentu:	Working Paper
Popis:	This paper focuses on approximation and learning performance analysis for deep convolutional neural networks with zero-padding and max-pooling. We prove that, to approximate $r$-smooth function, the approximation rates of deep convolutional neural networks with depth $L$ are of order $ (L^2/\log L)^{-2r/d} $, which is optimal up to a logarithmic factor. Furthermore, we deduce almost optimal learning rates for implementing empirical risk minimization over deep convolutional neural networks. Comment: 15 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.03259 Zobrazit plný text záznamu View this record from Arxiv