This paper presents a new approach, called perturb-max, for high-dimensional statistical
inference in graphical models that is based on applying random perturbations followed by …

The maximum a-posteriori (MAP) perturbation framework has emerged as a useful approach
for inference and learning in high dimensional complex models. By maximizing a randomly …

A substantial amount of research in the elds of statistics, machine learning and signal
processing during the last three decades considers the problem of variable selection for …

We study the behavior of the posterior distribution in high-dimensional Bayesian Gaussian
linear regression models having $ p\gg n $, with $ p $ the number of predictors and $ n $ the …

We provide a general theory of the expectation-maximization (EM) algorithm for inferring
high dimensional latent variable models. In particular, we make two contributions:(i) For …

Risk estimation is at the core of many learning systems. The importance of this problem has
motivated researchers to propose different schemes, such as cross validation, generalized …

Fitting high-dimensional statistical models often requires the use of non-linear parameter
estimation procedures. As a consequence, it is generally impossible to obtain an exact …

We provide a general theory of the expectation-maximization (EM) algorithm for inferring
high dimensional latent variable models. In particular, we make two contributions:(i) For …

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 …

In this paper, we study the problem of estimating latent variable models with arbitrarily
corrupted samples in high dimensional space (ie, d ≫ nd≫ n) where the underlying …