Timezone: »

Generalisation error in learning with random features and the hidden manifold model
Federica Gerace · Bruno Loureiro · Florent Krzakala · Marc Mezard · Lenka Zdeborova

Wed Jul 15 01:00 PM -- 01:45 PM & Thu Jul 16 02:00 AM -- 02:45 AM (PDT) @ Virtual

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.

Author Information

Federica Gerace (Institut de Physique Théorique)
Bruno Loureiro (Université de Paris Saclay)

Bruno Loureiro is currently a research scientist at the "Information, Learning and Physics" (IdePHICS) laboratory at EPFL, working on the crossroads between Machine Learning and Statistical Physics. Before moving to EPFL, he was a postdoctoral researcher at the Institut de Physique Théorique (IPhT) in Paris, and received his PhD from the University of Cambridge with a thesis on the applications of AdS/CFT to disordered quantum field theories.

Florent Krzakala (ENS)
Marc Mezard (ENS)
Lenka Zdeborova (CNRS)

More from the Same Authors