Saved in:
Bibliographic Details
Main Author: Dus, Mathias
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.22897
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917234876612608
author Dus, Mathias
author_facet Dus, Mathias
contents Training deep neural networks and Physics-Informed Neural Networks (PINNs) often leads to ill-conditioned and stiff optimization problems. A key structural feature of these models is that they are linear in the output-layer parameters and nonlinear in the hiddenlayer parameters, yielding a separable nonlinear least-squares formulation. In this work, we study the classical variable projection (VarPro) method for such problems in the context of deep neural networks. We provide a geometric formulation on the Grassmannian and analyze the structure of critical points and convergence properties of the reduced problem. When the feature map is parametrized by a neural network, we show that these properties persist except in rank-deficient regimes, which we address via a regularized Grassmannian framework. Numerical experiments for regression and PINNs, including an efficient solver for the heat equation, illustrate the practical effectiveness of the approach.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22897
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Grassmannian Geometry and Global Convergence of Variable Projection for Neural Networks
Dus, Mathias
Optimization and Control
Training deep neural networks and Physics-Informed Neural Networks (PINNs) often leads to ill-conditioned and stiff optimization problems. A key structural feature of these models is that they are linear in the output-layer parameters and nonlinear in the hiddenlayer parameters, yielding a separable nonlinear least-squares formulation. In this work, we study the classical variable projection (VarPro) method for such problems in the context of deep neural networks. We provide a geometric formulation on the Grassmannian and analyze the structure of critical points and convergence properties of the reduced problem. When the feature map is parametrized by a neural network, we show that these properties persist except in rank-deficient regimes, which we address via a regularized Grassmannian framework. Numerical experiments for regression and PINNs, including an efficient solver for the heat equation, illustrate the practical effectiveness of the approach.
title Grassmannian Geometry and Global Convergence of Variable Projection for Neural Networks
topic Optimization and Control
url https://arxiv.org/abs/2601.22897