Novel Proximal Gradient Methods for Nonnegative Matrix Factorization with Sparsity Constraints

DOI10.1137/19M1271750zbMath1442.90154OpenAlexW3007620966MaRDI QIDQ5108481

Marc Teboulle, Yakov Vaisbourd

Publication date: 4 May 2020

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/19m1271750

zbMATH Keywords

global convergencenonnegative matrix factorizationsparsity constraintsnon-Euclidean Bregman distanceproximal gradient algorithmsessentially cyclic block proximal gradientKurdyka-łosiajewicz propertynonconvex nonsmooth composite minimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Numerical optimization and variational techniques (65K10) Numerical methods based on nonlinear programming (49M37)

Related Items

Block Bregman Majorization Minimization with Extrapolation, Global convergence of model function based Bregman proximal minimization algorithms, A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity, Nested alternating minimization with FISTA for non-convex and non-smooth optimization problems, Algorithms for nonnegative matrix factorization with the Kullback-Leibler divergence

Uses Software

• CLUTO
• NeNMF

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Global convergence of modified multiplicative updates for nonnegative matrix factorization
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• On gradients of functions definable in o-minimal structures
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Document clustering using nonnegative matrix factorization
• Fast Nonnegative Matrix Factorization: An Active-Set-Like Method and Comparisons
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• On the Complexity of Nonnegative Matrix Factorization
• Hierarchical ALS Algorithms for Nonnegative Matrix and 3D Tensor Factorization
• Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
• NeNMF: An Optimal Gradient Method for Nonnegative Matrix Factorization
• First Order Methods Beyond Convexity and Lipschitz Gradient Continuity with Applications to Quadratic Inverse Problems
• A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization
• Unifying Abstract Inexact Convergence Theorems and Block Coordinate Variable Metric iPiano
• Learning the parts of objects by non-negative matrix factorization
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• Projected Gradient Methods for Nonnegative Matrix Factorization
• A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications
• Convergence of a block coordinate descent method for nondifferentiable minimization