A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization
From MaRDI portal
Publication:4621522
DOI10.1109/TSP.2017.2757914zbMATH Open1414.94747arXiv1609.00951OpenAlexW2963774283MaRDI QIDQ4621522FDOQ4621522
Publication date: 12 February 2019
Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)
Abstract: 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.
Full work available at URL: https://arxiv.org/abs/1609.00951
Cited In (5)
- Title not available (Why is that?)
- Multiplicative Updates for NMF with $\beta$-Divergences under Disjoint Equality Constraints
- Novel Proximal Gradient Methods for Nonnegative Matrix Factorization with Sparsity Constraints
- A convergent algorithm for bi-orthogonal nonnegative matrix tri-factorization
- A novel update rule of HALS algorithm for nonnegative matrix factorization and Zangwill's global convergence
This page was built for publication: A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621522)
