This is an interim version of our Electronic Legal Deposit Catalogue-eJournals and eBooks while we continue to recover from a cyber-attack.
Generalisation error in learning with random features and the hidden manifold model*This article is an updated version of: Gerace F, Loureiro B, Krzakala F, Mezard M and Zdeborova L 2020 Generalisation error in learning with random features and the hidden manifold model Proc. 37th Int. Conf. Machine Learning vol 119 ed H D III and A Singh pp 3452–62. (29th December 2021)
Record Type:
Journal Article
Title:
Generalisation error in learning with random features and the hidden manifold model*This article is an updated version of: Gerace F, Loureiro B, Krzakala F, Mezard M and Zdeborova L 2020 Generalisation error in learning with random features and the hidden manifold model Proc. 37th Int. Conf. Machine Learning vol 119 ed H D III and A Singh pp 3452–62. (29th December 2021)
Main Title:
Generalisation error in learning with random features and the hidden manifold model*This article is an updated version of: Gerace F, Loureiro B, Krzakala F, Mezard M and Zdeborova L 2020 Generalisation error in learning with random features and the hidden manifold model Proc. 37th Int. Conf. Machine Learning vol 119 ed H D III and A Singh pp 3452–62.
Abstract: We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden manifold model. We consider the high-dimensional regime and using the replica method from statistical physics, we provide a closed-form expression for the asymptotic generalisation performance in these problems, valid in both the under- and over-parametrised regimes and for a broad choice of generalised linear model loss functions. In particular, we show how to obtain analytically the so-called double descent behaviour for logistic regression with a peak at the interpolation threshold, we illustrate the superiority of orthogonal against random Gaussian projections in learning with random features, and discuss the role played by correlations in the data generated by the hidden manifold model. Beyond the interest in these particular problems, the theoretical formalism introduced in this manuscript provides a path to further extensions to more complex tasks.