Parallel Algorithms for Constrained Tensor Factorization via Alternating Direction Method of Multipliers

DOI10.1109/TSP.2015.2454476MaRDI QIDQ4580860zbMATH OpenFDO

Authors Nicholas D. Sidiropoulos, Athanasios P. Liavas

Publication date 22 August 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1409.2383

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Tensor factorization has proven useful in a wide range of applications, from sensor array processing to communications, speech and audio signal processing, and machine learning. With few recent exceptions, all tensor factorization algorithms were originally developed for centralized, in-memory computation on a single machine; and the few that break away from this mold do not easily incorporate practically important constraints, such as nonnegativity. A new constrained tensor factorization framework is proposed in this paper, building upon the Alternating Direction method of Multipliers (ADMoM). It is shown that this simplifies computations, bypassing the need to solve constrained optimization problems in each iteration; and it naturally leads to distributed algorithms suitable for parallel implementation on regular high-performance computing (e.g., mesh) architectures. This opens the door for many emerging big data-enabled applications. The methodology is exemplified using nonnegativity as a baseline constraint, but the proposed framework can more-or-less readily incorporate many other types of constraints. Numerical experiments are very encouraging, indicating that the ADMoM-based nonnegative tensor factorization (NTF) has high potential as an alternative to state-of-the-art approaches.

Cited in

(20)

• Smoothed _1-regularization-based line search for sparse signal recovery
• Alternating iterative methods for solving tensor equations with applications
• Global convergence of ADMM in nonconvex nonsmooth optimization
• A primal-dual algorithm for nonnegative N-th order CP tensor decomposition: application to fluorescence spectroscopy data analysis
• Dynamic behavior analysis via structured rank minimization
• Bregman reweighted alternating minimization and its application to image deblurring
• Multi-block nonconvex nonsmooth proximal ADMM: convergence and rates under Kurdyka-Łojasiewicz property
• An alternating direction method of multipliers for tensor complementarity problems
• A hybrid Bregman alternating direction method of multipliers for the linearly constrained difference-of-convex problems
• Perturbed proximal primal-dual algorithm for nonconvex nonsmooth optimization
• A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorization
• Exploiting Efficient Representations in Large-Scale Tensor Decompositions
• A general system for heuristic minimization of convex functions over non-convex sets
• Turbo‐SMT: Parallel coupled sparse matrix‐Tensor factorizations and applications
• Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints
• An alternating augmented Lagrangian method for constrained nonconvex optimization
• A simple effective heuristic for embedded mixed-integer quadratic programming
• A TT-based hierarchical framework for decomposing high-order tensors
• Parallel Algorithms for Computing the Tensor-Train Decomposition
• Quantization aware factorization for deep neural network compression

This page was built for publication: Parallel Algorithms for Constrained Tensor Factorization via Alternating Direction Method of Multipliers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580860)