Normalization effects on shallow neural networks and related asymptotic expansions

by   Jiahui Yu, et al.

We consider shallow (single hidden layer) neural networks and characterize their performance when trained with stochastic gradient descent as the number of hidden units N and gradient descent steps grow to infinity. In particular, we investigate the effect of different scaling schemes, which lead to different normalizations of the neural network, on the network's statistical output, closing the gap between the 1/√(N) and the mean-field 1/N normalization. We develop an asymptotic expansion for the neural network's statistical output pointwise with respect to the scaling parameter as the number of hidden units grows to infinity. Based on this expansion we demonstrate mathematically that to leading order in N there is no bias-variance trade off, in that both bias and variance (both explicitly characterized) decrease as the number of hidden units increases and time grows. In addition, we show that to leading order in N, the variance of the neural network's statistical output decays as the implied normalization by the scaling parameter approaches the mean field normalization. Numerical studies on the MNIST and CIFAR10 datasets show that test and train accuracy monotonically improve as the neural network's normalization gets closer to the mean field normalization.


page 1

page 2

page 3

page 4


Can Shallow Neural Networks Beat the Curse of Dimensionality? A mean field training perspective

We prove that the gradient descent training of a two-layer neural networ...

Scaling Limit of Neural Networks with the Xavier Initialization and Convergence to a Global Minimum

We analyze single-layer neural networks with the Xavier initialization i...

A Dynamical Central Limit Theorem for Shallow Neural Networks

Recent theoretical work has characterized the dynamics of wide shallow n...

A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization

The training dynamics of two-layer neural networks with batch normalizat...

Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit

We consider learning two layer neural networks using stochastic gradient...

The edge of chaos: quantum field theory and deep neural networks

We explicitly construct the quantum field theory corresponding to a gene...

On Sparsity in Overparametrised Shallow ReLU Networks

The analysis of neural network training beyond their linearization regim...