Largest Eigenvalues of the Conjugate Kernel of Single-Layered Neural Networks

Abstract

This paper is concerned with the asymptotic distribution of the largest eigenvalues for some nonlinear random matrix ensemble stemming from the study of neural networks. More precisely we consider $M=\frac{1}{m}Y{Y}^{\top }$ with $Y=f(WX)$ where $W$ and $X$ are random rectangular matrices with i.i.d. centered entries. This models the data covariance matrix or the Conjugate Kernel of a single layered random Feed-Forward Neural Network. The function $f$ is applied entrywise and can be seen as the activation function of the neural network. We show that the largest eigenvalue has the same limit (in probability) as that of some well-known linear random matrix ensembles. In particular, we relate the asymptotic limit of the largest eigenvalue for the nonlinear model to that of an information-plus-noise random matrix, establishing a possible phase transition depending on the function $f$ and the distribution of $W$ and $X$. This may be of interest for applications to machine learning.

27 pages, 15 figures

References in corpus (7)

• Deep Learning in Neural Networks: An Overview
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• The Loss Surfaces of Multilayer Networks
• Enhanced Convolutional Neural Tangent Kernels
• Kernel Alignment Risk Estimator: Risk Prediction from Training Data
• Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks
• Halting Time is Predictable for Large Models: A Universality Property and Average-case Analysis