Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchMachine learning

analiza aiqbench

This research establishes the quotient geometry of tensor ring (TR) decomposition, addressing its intrinsic manifold structure and gauge invariance to enable Riemannian optimization. By deriving explicit parameterizations for vertical and horizontal spaces under full-rank conditions, the study provides a rigorous mathematical foundation for efficient numerical methods in high-dimensional data analysis. While TR decompositions are widely used in machine learning applications, this work is fundamentally an advancement in optimization theory and differential geometry rather than a direct development of new AI models or quantum hardware.
Sursă care acoperăarXiv
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Quotient geometry of tensor ring decomposition

arXiv2 min de cititArticolul și perspectiva sunt în engleză.

arXiv:2601.21874v2 Announce Type: replace-cross Abstract: Differential geometries derived from tensor decompositions have been extensively studied and provided the foundations for a variety of efficient numerical methods. Despite the practical success of the tensor ring (TR) decomposition, its intrinsic geometry remains less understood, primarily due to the underlying ring structure and the resulting nontrivial gauge invariance. We establish the quotient geometry and immersed-submanifold structure of TR decomposition by imposing full-rank conditions on all unfolding matrices of the core tensors and capturing the gauge invariance. The intrinsic ring structure of TR leads to an analysis that is substantially different from other tensor formats. Additionally, for the uniform TR decomposition, where all core tensors are identical and the manifold structure is known, we derive explicit parameterizations for the vertical and horizontal spaces, which enable Riemannian optimization. Numerical experiments validate the developed geometries via tensor ring completion tasks.

Abstract:Differential geometries derived from tensor decompositions have been extensively studied and provided the foundations for a variety of efficient numerical methods. Despite the practical success of the tensor ring (TR) decomposition, its intrinsic geometry remains less understood, primarily due to the underlying ring structure and the resulting nontrivial gauge invariance. We establish the quotient geometry and immersed-submanifold structure of TR decomposition by imposing full-rank conditions on all unfolding matrices of the core tensors and capturing the gauge invariance. The intrinsic ring structure of TR leads to an analysis that is substantially different from other tensor formats. Additionally, for the uniform TR decomposition, where all core tensors are identical and the manifold structure is known, we derive explicit parameterizations for the vertical and horizontal spaces, which enable Riemannian optimization. Numerical experiments validate the developed geometries via tensor ring completion tasks.

Numerical Analysis (math.NA); Optimization and Control (math.OC); Quantum Physics (quant-ph)

arXiv:2601.21874 [math.NA]

(or arXiv:2601.21874v2 [math.NA] for this version)

https://doi.org/10.48550/arXiv.2601.21874 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Text integral sub licența deschisă a publicației · 238 cuvinte

Subiecte conexe