Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gu, Hyemin, Birmpa, Panagiota, Pantazis, Yannis, Rey-Bellet, Luc, Katsoulakis, Markos A.
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912003901095936
author Gu, Hyemin
Birmpa, Panagiota
Pantazis, Yannis
Rey-Bellet, Luc
Katsoulakis, Markos A.
author_facet Gu, Hyemin
Birmpa, Panagiota
Pantazis, Yannis
Rey-Bellet, Luc
Katsoulakis, Markos A.
contents We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples. These generative algorithms are particle-based and are constructed as gradient flows of Lipschitz-regularized Kullback-Leibler or other $f$-divergences, where data from a source distribution can be stably transported as particles, towards the vicinity of the target distribution. As a highlighted result in data integration, we demonstrate that the proposed algorithms correctly transport gene expression data points with dimension exceeding 54K, while the sample size is typically only in the hundreds.
format Preprint
id arxiv_https___arxiv_org_abs_2210_17230
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
Gu, Hyemin
Birmpa, Panagiota
Pantazis, Yannis
Rey-Bellet, Luc
Katsoulakis, Markos A.
Machine Learning
35Q84, 49Q22, 62B10, 65C35, 68T07, 94A17
We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples. These generative algorithms are particle-based and are constructed as gradient flows of Lipschitz-regularized Kullback-Leibler or other $f$-divergences, where data from a source distribution can be stably transported as particles, towards the vicinity of the target distribution. As a highlighted result in data integration, we demonstrate that the proposed algorithms correctly transport gene expression data points with dimension exceeding 54K, while the sample size is typically only in the hundreds.
title Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
topic Machine Learning
35Q84, 49Q22, 62B10, 65C35, 68T07, 94A17
url https://arxiv.org/abs/2210.17230