A Fully Dual Domain Decomposition Method for Extreme Learning Machines Using GenEO Spectral Coarse Spaces
Abstract
Extreme learning machines (ELMs) are a class of machine learning algorithms that randomly intialize and subsequently fix the hidden layer parameters, and solve for the last layer coefficients using a least squares method. ELMs have been successfully applied to the solution of various partial differential equations, but the cost of solving large least squares problems limits their use in large scale problems or when high accuracy is desired. To address this limitation, domain decomposition methods (DDMs) have been developed for ELMs, reducing training times via parallel computation. Yet these methods, even those incorporating a coarse space, have struggled with scalability. This paper introduces a novel nonoverlapping DDM for ELMs that treats and enforces continuity and flux conditions equally. Additive Schwarz preconditioners and GenEO (Generalized Eigenvalues problems in the Overlaps) coarse spaces are constructed to accelerate the method. Numerical experiments show the new method outperforms previous DDMs for ELMs in both iteration count and accuracy, especially for the Stokes and wave equations. Furthermore, weak scalability has been observed in up to 4,096 subdomains when employing GenEO coarse spaces.
Related
- On the Application of Hybrid Mixed Domain Decomposition Methods to Permanent Magnet Synchronous Machines
- Information-Geometric Selection for Validation-Guided Ensembles of Extreme Learning Machines: The LEA-EELM Framework
- fSRD: Fuzzy Spectral Region Decomposition -- Automated Multi Operator Koopman Representations via an Adaptive Spectral Learning Architecture
- Mapped Multi-Patch Spectral Extreme Learning Machine for Partial Differential Equations
- Dual-domain self-supervised feature alignment via spectral–spatial representation learning for deepfake anomaly detection
BibTeX
@misc{lee2026fully,
title = {{A Fully Dual Domain Decomposition Method for Extreme Learning Machines Using GenEO Spectral Coarse Spaces}},
author = {Chang-Ock Lee and Byungeun Ryoo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.08630},
eprint = {2609.08630},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.08630},
}
RIS
TY - UNPB
TI - A Fully Dual Domain Decomposition Method for Extreme Learning Machines Using GenEO Spectral Coarse Spaces
AU - Chang-Ock Lee
AU - Byungeun Ryoo
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.08630
UR - https://arxiv.org/abs/2609.08630
AB - Extreme learning machines (ELMs) are a class of machine learning algorithms that randomly intialize and subsequently fix the hidden layer parameters, and solve for the last layer coefficients using a least squares method. ELMs have been successfully applied to the solution of various partial differential equations, but the cost of solving large least squares problems limits their use in large scale problems or when high accuracy is desired. To address this limitation, domain decomposition methods (DDMs) have been developed for ELMs, reducing training times via parallel computation. Yet these methods, even those incorporating a coarse space, have struggled with scalability. This paper introduces a novel nonoverlapping DDM for ELMs that treats and enforces continuity and flux conditions equally. Additive Schwarz preconditioners and GenEO (Generalized Eigenvalues problems in the Overlaps) coarse spaces are constructed to accelerate the method. Numerical experiments show the new method outperforms previous DDMs for ELMs in both iteration count and accuracy, especially for the Stokes and wave equations. Furthermore, weak scalability has been observed in up to 4,096 subdomains when employing GenEO coarse spaces.
ER -