scholar.google.com › citations
We propose a generic framework based on a new stochastic variance-reduced gradient descent algorithm for accelerating nonconvex low-rank matrix recovery.
[PDF] Nonconvex Matrix Factorization from Rank-One Measurements
users.ece.cmu.edu › papers › ncvx_...
We consider the problem of recovering low- rank matrices from random rank-one measure- ments, which spans numerous applications in-.
This paper delivers improved theoretical guarantees for the convex programming approach in low-rank matrix estimation, in the presence of (1) random noise, ...
Abstract. We propose a unified framework to solve general low-rank plus sparse matrix recovery problems based on matrix factorization, which covers a broad ...
... nonconvex optimization can recover the underlying matrix exactly. In Chapter 2, we propose a model-free framework for nonconvex matrix completion: We.
Low-rank matrix factorization (LRMF) is a powerful approach that can recover useful information with low-rank features from corrupted data and has been ...
Missing: Restricted Properties
Abstract. We revisit the problem of robust principal component anal- ysis with features acting as prior side information. To this aim, a novel, elegant, ...
Missing: Restricted | Show results with:Restricted
Abstract. Techniques of matrix completion aim to impute a large portion of missing entries in a data matrix through a small portion of observed ones.
We propose a unified framework to solve general low-rank plus sparse matrix recov- ery problems based on matrix factorization, which covers a broad family ...
Abstract: We study the problem of recovery of matrices that are simulta- neously low rank and row and/or column sparse. Such matrices appear.
Missing: Properties | Show results with:Properties