Tensor Decomposition with Unaligned Observations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tang, Runshi, Kolda, Tamara, Zhang, Anru R.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916888797249536
author Tang, Runshi
Kolda, Tamara
Zhang, Anru R.
author_facet Tang, Runshi
Kolda, Tamara
Zhang, Anru R.
contents This paper presents a canonical polyadic (CP) tensor decomposition that addresses unaligned observations. The mode with unaligned observations is represented using functions in a reproducing kernel Hilbert space (RKHS). We introduce a versatile loss function that effectively accounts for various types of data, including binary, integer-valued, and positive-valued types. Additionally, we propose an optimization algorithm for computing tensor decompositions with unaligned observations, along with a stochastic gradient method to enhance computational efficiency. A sketching algorithm is also introduced to further improve efficiency when using the $\ell_2$ loss function. To demonstrate the efficacy of our methods, we provide illustrative examples using both synthetic data and an early childhood human microbiome dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14046
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tensor Decomposition with Unaligned Observations
Tang, Runshi
Kolda, Tamara
Zhang, Anru R.
Machine Learning
Numerical Analysis
Computation
Methodology
This paper presents a canonical polyadic (CP) tensor decomposition that addresses unaligned observations. The mode with unaligned observations is represented using functions in a reproducing kernel Hilbert space (RKHS). We introduce a versatile loss function that effectively accounts for various types of data, including binary, integer-valued, and positive-valued types. Additionally, we propose an optimization algorithm for computing tensor decompositions with unaligned observations, along with a stochastic gradient method to enhance computational efficiency. A sketching algorithm is also introduced to further improve efficiency when using the $\ell_2$ loss function. To demonstrate the efficacy of our methods, we provide illustrative examples using both synthetic data and an early childhood human microbiome dataset.
title Tensor Decomposition with Unaligned Observations
topic Machine Learning
Numerical Analysis
Computation
Methodology
url https://arxiv.org/abs/2410.14046