research
∙
06/03/2023
Random matrix theory and the loss surfaces of neural networks
Neural network models are one of the most successful approaches to machi...
share
research
∙
05/17/2022
Universal characteristics of deep neural network loss surfaces from random matrix theory
This paper considers several aspects of random matrix universality in de...
research
∙
03/15/2022
A novel sampler for Gauss-Hermite determinantal point processes with application to Monte Carlo integration
Determinantal points processes are a promising but relatively under-deve...
research
∙
02/12/2021
Applicability of Random Matrix Theory in Deep Learning
We investigate the local spectral statistics of the loss surface Hessian...
research
∙
01/07/2021
A spin-glass model for the loss surfaces of generative adversarial networks
We present a novel mathematical model that seeks to capture the key desi...
research
∙
04/08/2020