Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions

Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the textithidden manifold model, often under the simplifying assumption of a Gaussian distribution. We extend this framework by modeling inputs as Gaussian mixtures to better represent complex, real-world data. Through empirical and theoretical investigation, we demonstrate that with proper standardization, the learning dynamics converges to the behavior seen in the simple Gaussian case. This finding exhibits a form of universality, where diverse structured distributions yield results consistent with Gaussian assumptions, thereby strengthening the theoretical understanding of deep learning models.