Saved in:
Bibliographic Details
Main Authors: Willner, Marius, Trenti, Marco, Lebiedz, Dirk
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912628782137344
author Willner, Marius
Trenti, Marco
Lebiedz, Dirk
author_facet Willner, Marius
Trenti, Marco
Lebiedz, Dirk
contents Tree tensor networks (TTNs) are widely used in low-rank approximation and quantum many-body simulation. In this work, we present a formal analysis of the differential geometry underlying TTNs. Building on this foundation, we develop efficient first- and second-order optimization algorithms that exploit the intrinsic quotient structure of TTNs. Additionally, we devise a backpropagation algorithm for training TTNs in a kernel learning setting. We validate our methods through numerical experiments on a representative machine learning task.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning
Willner, Marius
Trenti, Marco
Lebiedz, Dirk
Optimization and Control
Other Condensed Matter
Machine Learning
15A69, 53C20, 65K10
Tree tensor networks (TTNs) are widely used in low-rank approximation and quantum many-body simulation. In this work, we present a formal analysis of the differential geometry underlying TTNs. Building on this foundation, we develop efficient first- and second-order optimization algorithms that exploit the intrinsic quotient structure of TTNs. Additionally, we devise a backpropagation algorithm for training TTNs in a kernel learning setting. We validate our methods through numerical experiments on a representative machine learning task.
title Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning
topic Optimization and Control
Other Condensed Matter
Machine Learning
15A69, 53C20, 65K10
url https://arxiv.org/abs/2507.21726