Mathematical theory of deep learning
Machine Learning
2026-01-16 v4 History and Overview
Abstract
This book provides an introduction to the mathematical analysis of deep learning. It covers fundamental results in approximation theory, optimization theory, and statistical learning theory, which are the three main pillars of deep neural network theory. Serving as a guide for students and researchers in mathematics and related fields, the book aims to equip readers with foundational knowledge on the topic. It prioritizes simplicity over generality, and presents rigorous yet accessible results to help build an understanding of the essential mathematical concepts underpinning deep learning.
Cite
@article{arxiv.2407.18384,
title = {Mathematical theory of deep learning},
author = {Philipp Petersen and Jakob Zech},
journal= {arXiv preprint arXiv:2407.18384},
year = {2026}
}