On the Equivalence between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint
Machine Learning
2023-09-01 v1 Machine Learning
Abstract
Implicit neural networks have demonstrated remarkable success in various tasks. However, there is a lack of theoretical analysis of the connections and differences between implicit and explicit networks. In this paper, we study high-dimensional implicit neural networks and provide the high dimensional equivalents for the corresponding conjugate kernels and neural tangent kernels. Built upon this, we establish the equivalence between implicit and explicit networks in high dimensions.
Keywords
Cite
@article{arxiv.2308.16425,
title = {On the Equivalence between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint},
author = {Zenan Ling and Zhenyu Liao and Robert C. Qiu},
journal= {arXiv preprint arXiv:2308.16425},
year = {2023}
}
Comments
Accepted by Workshop on High-dimensional Learning Dynamics, ICML 2023, Honolulu, Hawaii