The role of regularization in classification of high-dimensional noisy Gaussian mixture - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

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

(1) , (2) , (3) , (1)
1
2
3

Abstract

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.
Fichier principal
Vignette du fichier
2002.11544.pdf (752.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

cea-02529853 , version 1 (02-04-2020)

Identifiers

Cite

Francesca Mignacco, Florent Krzakala, Yue M. Lu, Lenka Zdeborová. The role of regularization in classification of high-dimensional noisy Gaussian mixture. International Conference on Machine Learning, Jun 2020, Virtual event, France. pp.6874-6883. ⟨cea-02529853⟩
104 View
119 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More