Saved in:
Bibliographic Details
Main Authors: Luo, Róisín, McDermott, James, O'Riordan, Colm
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.03764
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909901317472256
author Luo, Róisín
McDermott, James
O'Riordan, Colm
author_facet Luo, Róisín
McDermott, James
O'Riordan, Colm
contents We present a theoretical framework for deriving the general $n$-th order Fréchet derivatives of singular values in real rectangular matrices, by leveraging reduced resolvent operators from Kato's analytic perturbation theory for self-adjoint operators. Deriving closed-form expressions for higher-order derivatives of singular values is notoriously challenging through standard matrix-analysis techniques. To overcome this, we treat a real rectangular matrix as a compact operator on a finite-dimensional Hilbert space, and embed the rectangular matrix into a block self-adjoint operator so that non-symmetric perturbations are captured. Applying Kato's asymptotic eigenvalue expansion to this construction, we obtain a general, closed-form expression for the infinitesimal $n$-th order spectral variations. Specializing to $n=2$ and deploying on a Kronecker-product representation with matrix convention yield the Hessian of a singular value, not found in literature. By bridging abstract operator-theoretic perturbation theory with matrices, our framework equips researchers with a practical toolkit for higher-order spectral sensitivity studies in random matrix applications (e.g., adversarial perturbation in deep learning).
format Preprint
id arxiv_https___arxiv_org_abs_2506_03764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Higher-Order Singular-Value Derivatives of Rectangular Real Matrices
Luo, Róisín
McDermott, James
O'Riordan, Colm
Machine Learning
We present a theoretical framework for deriving the general $n$-th order Fréchet derivatives of singular values in real rectangular matrices, by leveraging reduced resolvent operators from Kato's analytic perturbation theory for self-adjoint operators. Deriving closed-form expressions for higher-order derivatives of singular values is notoriously challenging through standard matrix-analysis techniques. To overcome this, we treat a real rectangular matrix as a compact operator on a finite-dimensional Hilbert space, and embed the rectangular matrix into a block self-adjoint operator so that non-symmetric perturbations are captured. Applying Kato's asymptotic eigenvalue expansion to this construction, we obtain a general, closed-form expression for the infinitesimal $n$-th order spectral variations. Specializing to $n=2$ and deploying on a Kronecker-product representation with matrix convention yield the Hessian of a singular value, not found in literature. By bridging abstract operator-theoretic perturbation theory with matrices, our framework equips researchers with a practical toolkit for higher-order spectral sensitivity studies in random matrix applications (e.g., adversarial perturbation in deep learning).
title Higher-Order Singular-Value Derivatives of Rectangular Real Matrices
topic Machine Learning
url https://arxiv.org/abs/2506.03764