A Generalization Bound of Deep Neural Networks for Dependent Data
Machine Learning
2023-10-10 v1 Machine Learning
Abstract
Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid). This assumption may not hold in real-life applications such as evolutionary biology, infectious disease epidemiology, and stock price prediction. This work establishes a generalization bound of feed-forward neural networks for non-stationary -mixing data.
Keywords
Cite
@article{arxiv.2310.05892,
title = {A Generalization Bound of Deep Neural Networks for Dependent Data},
author = {Quan Huu Do and Binh T. Nguyen and Lam Si Tung Ho},
journal= {arXiv preprint arXiv:2310.05892},
year = {2023}
}