Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

arXiv:2605. 22010v1 Announce Type: new Abstract: We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{\hat{\rho}t^m}$ to its infinite-width counterpart $f{\rho_t^{MF}}$, which evolves in the mean-field dynamics.