Several recent trends in machine learning theory and practice, from the design of state-of-
the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under …

We examine a class of stochastic deep learning models with a tractable method to compute
information-theoretic quantities. Our contributions are three-fold:(i) We show how entropies …

This paper studies convergence of empirical measures smoothed by a Gaussian kernel.
Specifically, consider approximating P* N σ, for N σ=△ N (0, σ 2 I d), by P̑ n* N σ under …

At the heart of machine learning lies the question of generalizability of learned rules over
previously unseen data. While over-parameterized models based on neural networks are …

Deep generative priors offer powerful models for complex-structured data, such as images,
audio, and text. Using these priors in inverse problems typically requires estimating the input …

Deep generative networks provide a powerful tool for modeling complex data in a wide
range of applications. In inverse problems that use these networks as generative priors on …

Using a low-dimensional parametrization of signals is a generic and powerful way to
enhance performance in signal processing and statistical inference. A very popular and …

We study estimation in the linear model, in a Bayesian setting where has an entrywise iid
prior and the design is rotationally-invariant in law. In the large system limit as dimension …

There has been definite progress recently in proving the variational single-letter formula
given by the heuristic replica method for various estimation problems. In particular, the …

This article studies a high-dimensional inference problem involving the matrix tensor product
of random matrices. This problem generalizes a number of contemporary data science …