Identifiability in Exact Two-Layer Sparse Matrix Factorization

10/04/2021
by   Léon Zheng, et al.
0

Sparse matrix factorization is the problem of approximating a matrix Z by a product of L sparse factors X^(L) X^(L–1). .. X^(1). This paper focuses on identifiability issues that appear in this problem, in view of better understanding under which sparsity constraints the problem is well-posed. We give conditions under which the problem of factorizing a matrix into two sparse factors admits a unique solution, up to unavoidable permutation and scaling equivalences. Our general framework considers an arbitrary family of prescribed sparsity patterns, allowing us to capture more structured notions of sparsity than simply the count of nonzero entries. These conditions are shown to be related to essential uniqueness of exact matrix decomposition into a sum of rank-one matrices, with structured sparsity constraints. A companion paper further exploits these conditions to derive identifiability properties in multilayer sparse matrix factorization of some well-known matrices like the Hadamard or the discrete Fourier transform matrices.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/04/2021

Identifiability in Exact Multilayer Sparse Matrix Factorization

Many well-known matrices Z are associated to fast transforms correspondi...
research
11/13/2013

Sparse Matrix Factorization

We investigate the problem of factorizing a matrix into several sparse m...
research
12/01/2021

Spurious Valleys, Spurious Minima and NP-hardness of Sparse Matrix Factorization With Fixed Support

The problem of approximating a dense matrix by a product of sparse facto...
research
02/12/2016

Pursuits in Structured Non-Convex Matrix Factorizations

Efficiently representing real world data in a succinct and parsimonious ...
research
10/12/2019

Generalized Nullspace Property for Structurally Sparse Signals

We propose a new framework for studying the exact recovery of signals wi...
research
11/22/2017

Fast and Stable Pascal Matrix Algorithms

In this paper, we derive a family of fast and stable algorithms for mult...
research
02/25/2015

On Convolutional Approximations to Linear Dimensionality Reduction Operators for Large Scale Data Processing

In this paper, we examine the problem of approximating a general linear ...

Please sign up or login with your details

Forgot password? Click here to reset