arXiv · 2611.23321
Error Analysis of Deep Learning
Abstract
This review examines deep learning theory through the lens of error decomposition, systematically addressing approximation, statistical, and optimization errors. We trace the development of error analyses from bounds on individual error components to frameworks that account for all three. Using nonparametric regression and the Deep Ritz Method as dual running examples, we demonstrate how these analyses apply across fundamentally different loss structures. We then review representative analyses in scientific machine learning, generative learning, reinforcement learning, representation learning, and large language models, showing how learning errors affect solutions, distributions, and predictions through problem-specific arguments. Throughout, we clarify which error components are controlled, how they are combined, and what assumptions are needed to obtain guarantees for trained networks.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yuling Jiao, Peiying Wu, Jerry Zhijian Yang, Pingwen Zhang. 2026-11-15. Error Analysis of Deep Learning. https://searcharxiv.com/abs/2611.23321
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.