Infinite ResNets are Gaussian Mean ODEs
Organizations: Institute of Mathematics, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland · Department of Mathematics, National University of Singapore, Singapore
Abstract
Understanding the training dynamics of deep neural networks in large-scale limits is a question both of foundational and of practical importance. Prior works have obtained such descriptions through dynamical mean field theory (DMFT), yielding a system of non-Markovian dynamics that are challenging to analyze and that obscure the optimization structure of the original dynamics. In this paper, we obtain instead a simple description of the large-scale limit training dynamics for ResNets in standard shape scalings and in the branch scaling that allows maximal (local) feature updates. For a model trained with gradient descent (GD) from a random initialization, the limit dynamics is simply GD on a Neural Mean ODE with Gaussian initial weights. Our analysis covers population or empirical risk GD in the joint limit of large width, depth and embedding, input, and output dimensions. We obtain approximation scaling laws that depend on the shape of the ResNet and the covariance spectrum of the data. We also illustrate the flexibility of our approach by discussing Mixture of Expert models, where likewise the limit admits an intuitive (nested) Mean ODE description.
Figures & tables
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Neural Network Training Dynamics
Neural network training dynamics studies how parameters and representations change during optimization and how those changes shape learning, stability, and generalization.
See all 549 papers