Generative Modeling via Hierarchical Tensor Sketching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Yifan, Chen, Yian, Stoudenmire, E. Miles, Khoo, Yuehaw
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911364332650496
author Peng, Yifan
Chen, Yian
Stoudenmire, E. Miles
Khoo, Yuehaw
author_facet Peng, Yifan
Chen, Yian
Stoudenmire, E. Miles
Khoo, Yuehaw
contents We propose a hierarchical tensor-network approach for approximating high-dimensional probability density via empirical distribution. This leverages randomized singular value decomposition (SVD) techniques and involves solving linear equations for tensor cores in this tensor network. The complexity of the resulting algorithm scales linearly in the dimension of the high-dimensional density. An analysis of estimation error demonstrates the effectiveness of this method through several numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2304_05305
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generative Modeling via Hierarchical Tensor Sketching
Peng, Yifan
Chen, Yian
Stoudenmire, E. Miles
Khoo, Yuehaw
Numerical Analysis
Machine Learning
15A69, 62Gxx
We propose a hierarchical tensor-network approach for approximating high-dimensional probability density via empirical distribution. This leverages randomized singular value decomposition (SVD) techniques and involves solving linear equations for tensor cores in this tensor network. The complexity of the resulting algorithm scales linearly in the dimension of the high-dimensional density. An analysis of estimation error demonstrates the effectiveness of this method through several numerical experiments.
title Generative Modeling via Hierarchical Tensor Sketching
topic Numerical Analysis
Machine Learning
15A69, 62Gxx
url https://arxiv.org/abs/2304.05305