Random features and polynomial rules

arXiv:2402.10164v1 Announce Type: cross
Abstract: Random features models play a distinguished role in the theory of deep learning, describing the behavior of neural networks close to their infinite-width limit. In this work, we present a thorough analysis of the generalization performance of random features models for generic supervised learning problems with Gaussian data. Our approach, built with tools from the statistical mechanics of disordered systems, maps the random features model to an equivalent polynomial model, and allows us to plot …

abstract analysis arxiv behavior cond-mat.dis-nn cs.lg data deep learning features networks neural networks performance polynomial random role rules supervised learning theory type work