The role of regularization in classification of high-dimensional noisy Gaussian mixture

ICML 2020

The role of regularization in classification of high-dimensional noisy Gaussian mixture

Jul 12, 2020
|
52 views
|
Details
We consider a high-dimensional mixture of two Gaussians in the noisy regime where even an oracle knowing the centers of the clusters misclassifies a small but finite fraction of the points. We provide a rigorous analysis of the generalization error of regularized convex classifiers, including ridge, hinge and logistic regression, in the high-dimensional limit where the number $n$ of samples and their dimension $d$ go to infinity while their ratio is fixed to $\alpha= n/d$. We discuss surprising effects of the regularization that in some cases allows to reach the Bayes-optimal performances. We also illustrate the interpolation peak at low regularization, and analyze the role of the respective sizes of the two clusters. Speakers: Francesca Mignacco, Florent Krzakala, Yue M. Lu, Lenka Zdeborova

Comments
loading...