paper-with-me

홈 › Papers

Riemannian Optimization on Tree Tensor Networks with Application in Machine Learning

2025-07-29 · Marius Willner, Marco Trenti, Dirk Lebiedz arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.21726

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Natural Riemannian gradient for learning functional tensor networks

2026-04-10 · Nikolas Klug, Michael Ulbrich, André Uschmajew, Marius Willner arxiv

We consider machine learning tasks with low-rank functional tree tensor networks (TTN) as the learning model. While in the case of least-squares regression, low-rank functional TTNs can be efficiently optimized using alt…

Automatic differentiation for Riemannian optimization on low-rank matrix and tensor-train manifolds

2021-03-27 · Alexander Novikov, Maxim Rakhuba, Ivan Oseledets

In scientific computing and machine learning applications, matrices and more general multidimensional arrays (tensors) can often be approximated with the help of low-rank decompositions. Since matrices and tensors of fix…

Riemannian optimization

Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold

2025-10-01 · Ke Xu, Yuefeng Han arxiv

Recovering a low-CP-rank tensor from noisy linear measurements is a central challenge in high-dimensional data analysis, with applications spanning tensor PCA, tensor regression, and beyond. We exploit the intrinsic geom…

TensorFlow RiemOpt: a library for optimization on Riemannian manifolds

2021-05-27 · Oleg Smirnov

The adoption of neural networks and deep learning in non-Euclidean domains has been hindered until recently by the lack of scalable and efficient learning frameworks. Existing toolboxes in this space were mainly motivate…

BIG-bench Machine Learning

Ultrahyperbolic Representation Learning

2020-07-01 · NeurIPS 2020 12 · Marc T. Law, Jos Stam

In machine learning, data is usually represented in a (flat) Euclidean space where distances between points are along straight lines. Researchers have recently considered more exotic (non-Euclidean) Riemannian manifolds …

Representation Learning