Convergence Analysis of Block Newton Methods for 1D Shallow Neural Network Approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhiqiang, Doktorova, Anastassia, Falgout, Robert D., Herrera, César
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910050190098432
author Cai, Zhiqiang
Doktorova, Anastassia
Falgout, Robert D.
Herrera, César
author_facet Cai, Zhiqiang
Doktorova, Anastassia
Falgout, Robert D.
Herrera, César
contents This paper analyzes local convergence of the block Newton (BN) method introduced in [5, 6] for one-dimensional shallow neural network approximation to functions and diffusion-reaction problems. The BN method consists of the 2x2 block nonlinear Gauss-Seidel, linear Gauss-Seidel, or Jacobi method for outer iteration and the Newton method for inner iteration. The blocks are corresponding to the linear and the nonlinear parameters. Under some reasonable assumptions, we establish local convergence of the BN methods as well as the reduced BN (rBN) method for one-dimensional diffusion-reaction problems and least-squares function approximation. Unlike common optimization methods, the rBN allows for the reduction of the number of parameters during the optimization process when some neurons contribute little to the approximation or are at nearly optimal locations.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12559
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Convergence Analysis of Block Newton Methods for 1D Shallow Neural Network Approximation
Cai, Zhiqiang
Doktorova, Anastassia
Falgout, Robert D.
Herrera, César
Numerical Analysis
This paper analyzes local convergence of the block Newton (BN) method introduced in [5, 6] for one-dimensional shallow neural network approximation to functions and diffusion-reaction problems. The BN method consists of the 2x2 block nonlinear Gauss-Seidel, linear Gauss-Seidel, or Jacobi method for outer iteration and the Newton method for inner iteration. The blocks are corresponding to the linear and the nonlinear parameters. Under some reasonable assumptions, we establish local convergence of the BN methods as well as the reduced BN (rBN) method for one-dimensional diffusion-reaction problems and least-squares function approximation. Unlike common optimization methods, the rBN allows for the reduction of the number of parameters during the optimization process when some neurons contribute little to the approximation or are at nearly optimal locations.
title Convergence Analysis of Block Newton Methods for 1D Shallow Neural Network Approximation
topic Numerical Analysis
url https://arxiv.org/abs/2602.12559