We prove a universality theorem for learning with random features. Our result shows that, in
terms of training and generalization errors, a random feature model with a nonlinear …

Neural networks in the lazy training regime converge to kernel machines. Can neural
networks in the rich feature learning regime learn a kernel machine with a data-dependent …

Generalised linear models for multi-class classification problems are one of the fundamental
building blocks of modern machine learning tasks. In this manuscript, we characterise the …

In this manuscript we consider Kernel Ridge Regression (KRR) under the Gaussian design.
Exponents for the decay of the excess generalization error of KRR have been reported in …

Approximate message passing (AMP) algorithms have become an important element of high-
dimensional statistical inference, mostly due to their adaptability and concentration …

From the sampling of data to the initialisation of parameters, randomness is ubiquitous in
modern Machine Learning practice. Understanding the statistical fluctuations engendered …

Sharp global convergence guarantees for iterative nonconvex optimization with random data
Page 1 The Annals of Statistics 2023, Vol. 51, No. 1, 179–210 https://doi.org/10.1214/22-AOS2246 …

We provide exact asymptotic expressions for the performance of regression by an $ L-$
layer deep random feature (RF) model, where the input is mapped through multiple random …

The recent progresses in Machine Learning opened the door to actual applications of
learning algorithms but also to new research directions both in the field of Machine Learning …

Recent evidence has shown the existence of a so-called double-descent and even triple-
descent behavior for the generalization error of deep-learning models. This important …