
MW
Marius Willner, Marco Trenti, Dirk Lebiedz
· 1 min read
ResearcharXiv cs.LG
Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning
arXiv:2507.21726v3 Announce Type: replace-cross
Abstract: 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 quotient geometry underlying the TTN parameter space. Our framework allows for arbitrary horizontal distributions, and we develop efficient first- and second-order optimization algorithms that exploit this geometry. Additionally, we devise a backpropagation algorithm for training TTNs in a kernel learning setting. We validate our methods through numerical experiments on a representative digit classification task and reveal an important tradeoff between two different horizontal distributions that are available for TTNs: while one offers cleaner geometric statements, the other ultimately leads to more efficient algorithms.
Original source
This story was published by arXiv cs.LG and written by Marius Willner, Marco Trenti, Dirk Lebiedz. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


