Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

TL;DR

This paper investigates how finite width affects the dynamics and fluctuations of neural networks during training, revealing how feature learning influences variance reduction and learning speed, with empirical validation on CNNs.

Contribution

It provides a non-perturbative analysis of finite width effects in neural networks, extending dynamical mean field theory to characterize prediction fluctuations and feature learning impacts.

Findings

Finite width causes O(1/√width) fluctuations in network predictions.

Feature learning reduces variance of kernels and predictions in two-layer networks.

Initialization variance can slow down online learning and affect dynamics in CNNs.

Abstract

We analyze the dynamics of finite width effects in wide but finite feature learning neural networks. Starting from a dynamical mean field theory description of infinite width deep neural network kernel and prediction dynamics, we provide a characterization of the $O(1/\sqrt{\text{width}})$ fluctuations of the DMFT order parameters over random initializations of the network weights. Our results, while perturbative in width, unlike prior analyses, are non-perturbative in the strength of feature learning. In the lazy limit of network training, all kernels are random but static in time and the prediction variance has a universal form. However, in the rich, feature learning regime, the fluctuations of the kernels and predictions are dynamically coupled with a variance that can be computed self-consistently. In two layer networks, we show how feature learning can dynamically reduce the variance of the final tangent kernel and final network predictions. We also show how initialization variance can slow down online learning in wide but finite networks. In deeper networks, kernel variance can dramatically accumulate through subsequent layers at large feature learning strengths, but feature learning continues to improve the signal-to-noise ratio of the feature kernels. In discrete time, we demonstrate that large learning rate phenomena such as edge of stability effects can be well captured by infinite width dynamics and that initialization variance can decrease dynamically. For CNNs trained on CIFAR-10, we empirically find significant corrections to both the bias and variance of network dynamics due to finite width.