We study Glauber dynamics for sampling from discrete distributions μ on
...
The theory of influences in product measures has profound applications i...
Sparse linear regression is a central problem in high-dimensional statis...
We prove a new generalization bound that shows for any class of linear
p...
Deep generative models parametrized up to a normalizing constant (e.g.
e...
Sparse linear regression with ill-conditioned Gaussian random designs is...
We consider Ising models on the hypercube with a general interaction mat...
Variational Autoencoders (VAEs) are one of the most commonly used genera...
We study a localized notion of uniform convergence known as an "optimist...
Here we revisit the classic problem of linear quadratic estimation, i.e....
We introduce a framework for obtaining tight mixing times for Markov cha...
Metric Multidimensional scaling (MDS) is a classical method for generati...
The study of Markov processes and broadcasting on trees has deep connect...
We consider interpolation learning in high-dimensional linear regression...
Sparse linear regression is a fundamental problem in high-dimensional
st...
We introduce a notion called entropic independence for distributions μ
d...
We consider the problem of learning a tree-structured Ising model from d...
In this work we revisit two classic high-dimensional online learning
pro...
Normalizing flows are among the most popular paradigms in generative
mod...
Graphical models are powerful tools for modeling high-dimensional data, ...
In this paper we revisit some classic problems on classification under
m...
Arrow's Theorem concerns a fundamental problem in social choice theory: ...
The analysis of Belief Propagation and other algorithms for the
reconst...
Belief propagation is a fundamental message-passing algorithm for
probab...
Gaussian Graphical Models (GGMs) have wide-ranging applications in machi...
Reconstruction of population histories is a central problem in populatio...
The free energy is a key quantity of interest in Ising models, but
unfor...
There has been a large amount of interest, both in the past and particul...
Graphical models are a rich language for describing high-dimensional
dis...
We study the following question: given a massive Markov random field on ...
The mean field approximation to the Ising model is a canonical variation...
We study approximations of the partition function of dense graphical mod...
Recently, there has been considerable progress on designing algorithms w...