On Tensors, Sparsity, and Nonnegative Factorizations
From MaRDI portal
Publication:4918166
Abstract: Tensors have found application in a variety of fields, ranging from chemometrics to signal processing and beyond. In this paper, we consider the problem of multilinear modeling of sparse count data. Our goal is to develop a descriptive tensor factorization model of such data, along with appropriate algorithms and theory. To do so, we propose that the random variation is best described via a Poisson distribution, which better describes the zeros observed in the data as compared to the typical assumption of a Gaussian distribution. Under a Poisson assumption, we fit a model to observed data using the negative log-likelihood score. We present a new algorithm for Poisson tensor factorization called CANDECOMP-PARAFAC Alternating Poisson Regression (CP-APR) that is based on a majorization-minimization approach. It can be shown that CP-APR is a generalization of the Lee-Seung multiplicative updates. We show how to prevent the algorithm from converging to non-KKT points and prove convergence of CP-APR under mild conditions. We also explain how to implement CP-APR for large-scale sparse tensors and present results on several data sets, both real and simulated.
Recommendations
- Nonnegative tensor factorization, completely positive tensors, and a hierarchical elimination algorithm
- Solving sparse non-negative tensor equations: algorithms and applications
- Computing non-negative tensor factorizations
- Nonnegative tensor factorizations using an alternating direction method
- Non-negative matrix factorization with sparseness constraints
- Nonnegative Tensor Train Factorizations and Some Applications
- Nonnegative non-redundant tensor decomposition
- On tensor decomposition, sparse interpolation and Padé approximation
- Sparse non-negative tensor factorization using columnwise coordinate descent
- Algorithms for nonnegative tensor factorization
Cited in
(52)- Rank decomposition and symmetric rank decomposition over arbitrary fields
- scientific article; zbMATH DE number 97476 (Why is no real title available?)
- Generalized co-clustering analysis via regularized alternating least squares
- Multilayer tensor factorization with applications to recommender systems
- Tensor decompositions and sparse log-linear models
- Stochastic gradients for large-scale tensor decomposition
- Parsimonious Tensor Discriminant Analysis
- Alternating proximal gradient method for sparse nonnegative Tucker decomposition
- scientific article; zbMATH DE number 7370581 (Why is no real title available?)
- Low-rank matrix approximation in the infinity norm
- Covariate-adjusted tensor classification in high dimensions
- Parameter selection for nonnegative $l_1$ matrix/tensor sparse decomposition
- Bayesian factorizations of big sparse tensors
- WINTENDED: WINdowed TENsor decomposition for densification event detection in time-evolving networks
- On the complexity of robust PCA and \(\ell_1\)-norm low-rank matrix approximation
- An optimal statistical and computational framework for generalized tensor estimation
- scientific article; zbMATH DE number 7049742 (Why is no real title available?)
- Low-rank approximation and completion of positive tensors
- Multiplicative Updates for NMF with $\beta$-Divergences under Disjoint Equality Constraints
- Smoothed tensor quantile regression estimation for longitudinal data
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- A general framework for tensor screening through smoothing
- Sketch-based multiplicative updating algorithms for symmetric nonnegative tensor factorizations with applications to face image clustering
- Cyclic coordinate-update algorithms for fixed-point problems: analysis and applications
- MuLOT: multi-level optimization of the canonical polyadic tensor decomposition at large-scale
- Taming numerical imprecision by adapting the KL divergence to negative probabilities
- Algorithms for nonnegative matrix factorization with the Kullback-Leibler divergence
- STORE: sparse tensor response regression and neuroimaging analysis
- A primal-dual algorithm for nonnegative N-th order CP tensor decomposition: application to fluorescence spectroscopy data analysis
- A literature survey of matrix methods for data science
- Variational auto-encoder based Bayesian Poisson tensor factorization for sparse and imbalanced count data
- Generalized Tensor Decomposition With Features on Multiple Modes
- Sparse random tensors: concentration, regularization and applications
- Best sparse rank-1 approximation to higher-order tensors via a truncated exponential induced regularizer
- Legendre decomposition for tensors
- Several approximation algorithms for sparse best rank-1 approximation to higher-order tensors
- Newton-based optimization for Kullback-Leibler nonnegative tensor factorizations
- Tensor sparsification via a bound on the spectral norm of random tensors: Algorithm 1.
- Nonnegative tensor decomposition
- Generating hidden Markov models from process models through nonnegative tensor factorization
- Nonnegative rank depends on the field
- Generalized canonical polyadic tensor decomposition
- Nonnegative non-redundant tensor decomposition
- Literature survey on low rank approximation of matrices
- A unified global convergence analysis of multiplicative update rules for nonnegative matrix factorization
- On Theorem 10 in “On Polar Polytopes and the Recovery of Sparse Representations” [Sep 07 3188-3195]
- Fast and Separable Estimation in High-Dimensional Tensor Gaussian Graphical Models
- Multiplicative algorithms for symmetric nonnegative tensor factorizations and its applications
- Exponential family tensor completion with auxiliary information
- Analysis on a nonnegative matrix factorization and its applications
- Clustering Boolean tensors
- On cones of nonnegative quartic forms
This page was built for publication: On Tensors, Sparsity, and Nonnegative Factorizations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4918166)
