The problem of completing a low-rank matrix from a subset of its entries is often encountered in the analysis of incomplete data sets exhibiting an underlying factor model with app...
This paper presents a unified view of a number of dimension reduction techniques under the common framework of tensors. Specifically, it is established that PCA, and the recentl...
ABSTRACT: Linear function approximations based on random projections are proposed and justified for a class of fixed point and minimization problems. KEY WORDS: random projections,...
We analyze a class of estimators based on a convex relaxation for solving highdimensional matrix decomposition problems. The observations are the noisy realizations of the sum of ...
Alekh Agarwal, Sahand Negahban, Martin J. Wainwrig...