Equivariant and scale-free Tucker decomposition models
From MaRDI portal
Publication:516494
DOI10.1214/14-BA934zbMATH Open1359.62221arXiv1312.6397OpenAlexW2035182720MaRDI QIDQ516494FDOQ516494
Authors: Peter D. Hoff 
Publication date: 14 March 2017
Published in: Bayesian Analysis (Search for Journal in Brave)
Abstract: Analyses of array-valued datasets often involve reduced-rank array approximations, typically obtained via least-squares or truncations of array decompositions. However, least-squares approximations tend to be noisy in high-dimensional settings, and may not be appropriate for arrays that include discrete or ordinal measurements. This article develops methodology to obtain low-rank model-based representations of continuous, discrete and ordinal data arrays. The model is based on a parameterization of the mean array as a multilinear product of a reduced-rank core array and a set of index-specific orthogonal eigenvector matrices. It is shown how orthogonally equivariant parameter estimates can be obtained from Bayesian procedures under invariant prior distributions. Additionally, priors on the core array are developed that act as regularizers, leading to improved inference over the standard least-squares estimator, and providing robustness to misspecification of the array rank. This model-based approach is extended to accommodate discrete or ordinal data arrays using a semiparametric transformation model. The resulting low-rank representation is scale-free, in the sense that it is invariant to monotonic transformations of the data array. In an example analysis of a multivariate discrete network dataset, this scale-free approach provides a more complete description of data patterns.
Full work available at URL: https://arxiv.org/abs/1312.6397
Recommendations
- Hierarchical multilinear models for multiway data
- Separable covariance arrays via the Tucker product, with applications to multivariate relational data
- Tensor decompositions and sparse log-linear models
- Simplicity transformations for three-way arrays with symmetric slices, and applications to Tucker-3 models with sparse core arrays
- A new tensor decomposition
Bayesian inference (62F15) Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Social networks; opinion dynamics (91D30)
Cited In (10)
- Structured Shrinkage Priors
- Additive and multiplicative effects network models
- Adaptive shrinkage of singular values
- Estimation of a multiplicative correlation structure in the large dimensional case
- Factor uniqueness of the structural Parafac model
- A higher-order LQ decomposition for separable covariance models
- A Probit Tensor Factorization Model For Relational Learning
- ESTIMATION OF THE KRONECKER COVARIANCE MODEL BY QUADRATIC FORM
- Alternating Linear Scheme in a Bayesian Framework for Low-Rank Tensor Approximation
- Hierarchical multilinear models for multiway data
This page was built for publication: Equivariant and scale-free Tucker decomposition models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q516494)
