A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization

09/04/2016
by   Renbo Zhao, et al.
0

The multiplicative update (MU) algorithm has been extensively used to estimate the basis and coefficient matrices in nonnegative matrix factorization (NMF) problems under a wide range of divergences and regularizers. However, theoretical convergence guarantees have only been derived for a few special divergences without regularization. In this work, we provide a conceptually simple, self-contained, and unified proof for the convergence of the MU algorithm applied on NMF with a wide range of divergences and regularizers. Our main result shows the sequence of iterates (i.e., pairs of basis and coefficient matrices) produced by the MU algorithm converges to the set of stationary points of the non-convex NMF optimization problem. Our proof strategy has the potential to open up new avenues for analyzing similar problems in machine learning and signal processing.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2013

Max-Min Distance Nonnegative Matrix Factorization

Nonnegative Matrix Factorization (NMF) has been a popular representation...
research
10/30/2017

Stochastic variance reduced multiplicative update for nonnegative matrix factorization

Nonnegative matrix factorization (NMF), a dimensionality reduction and f...
research
06/20/2017

Frank-Wolfe Optimization for Symmetric-NMF under Simplicial Constraint

We propose a Frank-Wolfe (FW) solver to optimize the symmetric nonnegati...
research
03/14/2018

Multiplicative Updates for Elastic Net Regularized Convolutional NMF Under β-Divergence

We generalize the convolutional NMF by taking the β-divergence as the lo...
research
12/25/2021

Over-Parametrized Matrix Factorization in the Presence of Spurious Stationary Points

Motivated by the emerging role of interpolating machines in signal proce...
research
07/30/2016

Online Nonnegative Matrix Factorization with General Divergences

We develop a unified and systematic framework for performing online nonn...
research
10/18/2016

Fast L1-NMF for Multiple Parametric Model Estimation

In this work we introduce a comprehensive algorithmic pipeline for multi...

Please sign up or login with your details

Forgot password? Click here to reset