Universal characteristics of deep neural network loss surfaces from random matrix theory
This paper considers several aspects of random matrix universality in deep neural networks (DNNs). Motivated by recent experimental work, we use universal properties of random matrices related to local statistics to derive practical implications for DNNs based on a realistic model of their Hessians....
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
IOP Publishing
2022
|