Newton-Based Optimization for Nonnegative Tensor Factorizations
Authors:
- Samantha HansenSHSamantha Hansen
- Todd PlantengaTPTodd Plantenga
- Tamara G. KoldaTKTamara G. Kolda
Preprint
Abstract
Tensor factorizations with nonnegative constraints have found application in analyzing data from cyber traffic, social networks, and other areas. We consider application data best described as being generated by a Poisson process (e.g., count data), which leads to sparse tensors that can be modeled by sparse factor matrices. In this paper we investigate efficient techniques for computing an appropriate tensor factorization and propose new subproblem solvers within the standard alternating block variable approach. Our new methods exploit structure and reformulate the optimization problem as small independent subproblems. We employ bound-constrained Newton and quasi-Newton methods. We compare our algorithms against other codes, demonstrating superior speed for high accuracy results and the ability to quickly find sparse solutions.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Sparse non-negative tensor factorization using columnwise coordinate descentPattern Recognition, 2012
- A scalable optimization approach for fitting canonical tensor decompositionsJournal of Chemometrics, 2011
- Nonnegative tensor factorization as an alternative Csiszar–Tusnady procedure: algorithms, convergence, probabilistic interpretations and novel probabilistic tensor latent variable analysis algorithmsData Mining and Knowledge Discovery, 2010
- Fast Projection‐Based Methods for the Least Squares Nonnegative Matrix Approximation ProblemStatistical Analysis and Data Mining: An ASA Data Science Journal, 2007
- Positive tensor factorizationPattern Recognition Letters, 2001
- Learning the parts of objects by non-negative matrix factorizationNature, 1999
- A weighted non-negative least squares algorithm for three-way ‘PARAFAC’ factor analysisChemometrics and Intelligent Laboratory Systems, 1997
- Positive matrix factorization: A non‐negative factor model with optimal utilization of error estimates of data valuesEnvironmetrics, 1994
- Projected Newton Methods for Optimization Problems with Simple ConstraintsSIAM Journal on Control and Optimization, 1982
- Analysis of Individual Differences in Multidimensional Scaling Via an N-way Generalization of “Eckart-Young” DecompositionPsychometrika, 1970