Binary Component Decomposition Part I: The Positive-Semidefinite Case

07/31/2019
by   Richard Kueng, et al.
0

This paper studies the problem of decomposing a low-rank positive-semidefinite matrix into symmetric factors with binary entries, either {± 1} or {0,1}. This research answers fundamental questions about the existence and uniqueness of these decompositions. It also leads to tractable factorization algorithms that succeed under a mild deterministic condition. A companion paper addresses the related problem of decomposing a low-rank rectangular matrix into a binary factor and an unconstrained factor.

READ FULL TEXT
research
07/31/2019

Binary component decomposition Part II: The asymmetric case

This paper studies the problem of decomposing a low-rank matrix into a f...
research
01/18/2018

Computation of the Maximum Likelihood estimator in low-rank Factor Analysis

Factor analysis, a classical multivariate statistical technique is popul...
research
05/12/2021

A new perspective on low-rank optimization

A key question in many low-rank problems throughout optimization, machin...
research
11/29/2021

Local convergence of alternating low-rank optimization methods with overrelaxation

The local convergence of alternating optimization methods with overrelax...
research
04/28/2020

Denise: Deep Learning based Robust PCA for Positive Semidefinite Matrices

We introduce Denise, a deep learning based algorithm for decomposing pos...
research
07/05/2022

Improved Global Guarantees for the Nonconvex Burer–Monteiro Factorization via Rank Overparameterization

We consider minimizing a twice-differentiable, L-smooth, and μ-strongly ...
research
11/03/2018

Biconvex Landscape In SDP-Related Learning

Many machine learning problems can be reduced to learning a low-rank pos...

Please sign up or login with your details

Forgot password? Click here to reset