Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Robust Principal Component Analysis

12/30/2018
by   Salar Fattahi, et al.
0

This work is concerned with the non-negative robust principal component analysis (PCA), where the goal is to recover the dominant non-negative principal component of a data matrix precisely, where a number of measurements could be grossly corrupted with sparse and arbitrary large noise. Most of the known techniques for solving the robust PCA rely on convex relaxation methods by lifting the problem to a higher dimension, which significantly increase the number of variables. As an alternative, the well-known Burer-Monteiro approach can be used to cast the robust PCA as a non-convex and non-smooth ℓ_1 optimization problem with a significantly smaller number of variables. In this work, we show that the low-dimensional formulation of the symmetric and asymmetric positive robust PCA based on the Burer-Monteiro approach has benign landscape, i.e., 1) it does not have any spurious local solution, 2) has a unique global solution, and 3) its unique global solution coincides with the true components. An implication of this result is that simple local search algorithms are guaranteed to achieve a zero global optimality gap when directly applied to the low-dimensional formulation. Furthermore, we provide strong deterministic and statistical guarantees for the exact recovery of the true principal component. In particular, it is shown that a constant fraction of the measurements could be grossly corrupted and yet they would not create any spurious local solution.

READ FULL TEXT
research
01/07/2019

Stochastic Approximation Algorithms for Principal Component Analysis

Principal Component Analysis is a novel way of of dimensionality reducti...
research
07/09/2019

Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation

In this paper, we consider the problem of unsupervised video object segm...
research
10/20/2010

Robust PCA via Outlier Pursuit

Singular Value Decomposition (and Principal Component Analysis) is one o...
research
06/08/2015

Stay on path: PCA along graph paths

We introduce a variant of (sparse) PCA in which the set of feasible supp...
research
02/08/2022

Efficient Algorithms for High-Dimensional Convex Subspace Optimization via Strict Complementarity

We consider optimization problems in which the goal is find a k-dimensio...
research
10/21/2016

Convex Formulation for Kernel PCA and its Use in Semi-Supervised Learning

In this paper, Kernel PCA is reinterpreted as the solution to a convex o...
research
03/07/2018

An iALM-ICA-based Anti-Jamming DS-CDMA Receiver for LMS Systems

We consider a land mobile satellite communication system using spread sp...

Please sign up or login with your details

Forgot password? Click here to reset