Saved in:
Bibliographic Details
Main Authors: Arbel, Adi, Steinerberger, Stefan, Talmon, Ronen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14118
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913035760697344
author Arbel, Adi
Steinerberger, Stefan
Talmon, Ronen
author_facet Arbel, Adi
Steinerberger, Stefan
Talmon, Ronen
contents Given two symmetric positive-definite matrices $A, B \in \mathbb{R}^{n \times n}$, we study the spectral properties of the interpolation $A^{1-x} B^x$ for $0 \leq x \leq 1$. The presence of `common structures' in $A$ and $B$, eigenvectors pointing in a similar direction, can be investigated using this interpolation perspective. Generically, exact log-linearity of the operator norm $\|A^{1-x} B^x\|$ is equivalent to the existence of a shared eigenvector in the original matrices; stability bounds show that approximate log-linearity forces principal singular vectors to align with leading eigenvectors of both matrices. These results give rise to and provide theoretical justification for a multi-manifold learning framework that identifies common and distinct latent structures in multiview data.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14118
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Complex Interpolation of Matrices with an application to Multi-Manifold Learning
Arbel, Adi
Steinerberger, Stefan
Talmon, Ronen
Machine Learning
Spectral Theory
Given two symmetric positive-definite matrices $A, B \in \mathbb{R}^{n \times n}$, we study the spectral properties of the interpolation $A^{1-x} B^x$ for $0 \leq x \leq 1$. The presence of `common structures' in $A$ and $B$, eigenvectors pointing in a similar direction, can be investigated using this interpolation perspective. Generically, exact log-linearity of the operator norm $\|A^{1-x} B^x\|$ is equivalent to the existence of a shared eigenvector in the original matrices; stability bounds show that approximate log-linearity forces principal singular vectors to align with leading eigenvectors of both matrices. These results give rise to and provide theoretical justification for a multi-manifold learning framework that identifies common and distinct latent structures in multiview data.
title Complex Interpolation of Matrices with an application to Multi-Manifold Learning
topic Machine Learning
Spectral Theory
url https://arxiv.org/abs/2604.14118