research
∙
09/26/2020
The smoothed complexity of Frank-Wolfe methods via conditioning of random matrices and polytopes
Frank-Wolfe methods are popular for optimization over a polytope. One of...
share
research
∙
07/16/2020
Overcomplete order-3 tensor decomposition, blind deconvolution and Gaussian mixture models
We expand the family of tensors that can be efficiently decomposed and a...
research
∙
12/09/2019
Algebraic k-sets and generally neighborly embeddings
Given a set S of n points in R^d, a k-set is a subset of k points of S t...
research
∙
02/22/2017
Heavy-Tailed Analogues of the Covariance Matrix for ICA
Independent Component Analysis (ICA) is the problem of learning a square...
research
∙
09/02/2015
Heavy-tailed Independent Component Analysis
Independent component analysis (ICA) is the problem of efficiently recov...
research
∙
02/13/2015
A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA
Independent Component Analysis (ICA) is a popular model for blind signal...
research
∙
03/04/2014
The Hidden Convexity of Spectral Clustering
In recent years, spectral clustering has become a standard method for da...
research
∙
11/12/2013
The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures
In this paper we show that very large mixtures of Gaussians are efficien...
research
∙
11/09/2012
Efficient learning of simplices
We show an efficient algorithm for the following problem: Given uniforml...
research
∙
11/07/2012