Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
نویسندگان
چکیده
منابع مشابه
Nonconvex Low Rank Matrix Factorization via Inexact First Order Oracle
We study the low rank matrix factorization problem via nonconvex optimization. Compared with the convex relaxation approach, nonconvex optimization exhibits superior empirical performance for large scale low rank matrix estimation. However, the understanding of its theoretical guarantees is limited. To bridge this gap, we exploit the notion of inexact first order oracle, which naturally appears...
متن کاملNonconvex Matrix Factorization from Rank-One Measurements
We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural networks, among others. Our approach is to directly estimate the low-rank factor by minimizing a nonconvex quadratic loss function via vanilla gradient descen...
متن کاملA Nonconvex Optimization Framework for Low Rank Matrix Estimation
We study the estimation of low rank matrices via nonconvex optimization. Compared with convex relaxation, nonconvex optimization exhibits superior empirical performance for large scale instances of low rank matrix estimation. However, the understanding of its theoretical guarantees are limited. In this paper, we define the notion of projected oracle divergence based on which we establish suffic...
متن کاملLow-rank matrix factorization with attributes
We develop a new collaborative filtering (CF) method that combines both previously known users’ preferences, i.e. standard CF, as well as product/user attributes, i.e. classical function approximation, to predict a given user’s interest in a particular product. Our method is a generalized low rank matrix completion problem, where we learn a function whose inputs are pairs of vectors – the stand...
متن کاملNotes on Low-rank Matrix Factorization
Low-rank matrix factorization (MF) is an important technique in data science. The key idea of MF is that there exists latent structures in the data, by uncovering which we could obtain a compressed representation of the data. By factorizing an original matrix to low-rank matrices, MF provides a unified method for dimension reduction, clustering, and matrix completion. In this article we review ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Signal Processing
سال: 2019
ISSN: 1053-587X,1941-0476
DOI: 10.1109/tsp.2019.2937282