The rapid recent progress in machine learning (ML) has raised a number of scientific
questions that challenge the longstanding dogma of the field. One of the most important …

Consider supervised learning from iid samples {(y_i, x_i)} _ {i≤ n} where x_i∈ R_p are
feature vectors and y_i∈ R are labels. We study empirical risk minimization over a class of …

Teacher-student models provide a framework in which the typical-case performance of high-
dimensional supervised learning can be described in closed form. The assumptions of …

We consider the problem of learning a target function corresponding to a deep, extensive-
width, non-linear neural network with random Gaussian weights. We consider the asymptotic …

The goal in label-imbalanced and group-sensitive classification is to optimize relevant
metrics such as balanced error and equal opportunity. Classical methods, such as weighted …

A recent line of research has highlighted the existence of a``double descent''phenomenon in
deep learning, whereby increasing the number of training examples N causes the …

The growing literature on" benign overfitting" in overparameterized models has been mostly
restricted to regression or binary classification settings; however, most success stories of …

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

We address the problem of denoising data from a Gaussian mixture using a two-layer non-
linear autoencoder with tied weights and a skip connection. We consider the high …

We prove closed-form equations for the exact high-dimensional asymptotics of a family of
first-order gradient-based methods, learning an estimator (eg, M-estimator, shallow neural …