Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension. (arXiv:2205.13303v1 [stat.ML])

While classical in many theoretical settings, the assumption of Gaussian
i.i.d. inputs is often perceived as a strong limitation in the analysis of
high-dimensional learning. In this study, we redeem this line of work in the
case of generalized linear classification with random labels. Our main
contribution is a rigorous proof that data coming from a range of generative
models in high-dimensions have the same minimum training loss as Gaussian data
with corresponding data covariance. In particular, our theorem covers …

arxiv classifiers labels linear ml random