A new spherical transform with sign parameters gives the joint eigenvalue density and kernels for products of Pólya ensembles with Hermitian matrices.
The Dynamics of Learning: A Random Matrix Approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we introduce a random matrix-based framework to analyze the learning dynamics of a single-layer linear network on a binary classification problem, for data of simultaneously large dimension and size, trained by gradient descent. Our results provide rich insights into common questions in neural nets, such as overfitting, early stopping and the initialization of training, thereby opening the door for future studies of more elaborate structures and models appearing in today's neural networks.
fields
math.PR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Products of Complex Rectangular and Hermitian Random Matrices
A new spherical transform with sign parameters gives the joint eigenvalue density and kernels for products of Pólya ensembles with Hermitian matrices.