When random features beat the mesh. Benchmarking physics-informed extreme learning machines against finite elements
Loading...
Authors
Author (Corporation)
Publication date
25.02.2026
Type of student thesis
Course of study
Type
01A - Journal article
Editors
Editor (Corporation)
Supervisor
Parent work
IEEE Access
Special issue
DOI of the original publication
Link
Series
Series number
Volume
Issue / Number
Pages / Duration
1-12
Patent number
Publisher / Publishing institution
IEEE
Place of publication / Event location
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
Physics-informed extreme learning machines (PIELMs) have emerged as optimisation-free surrogates to gradient-based physics-informed neural networks, yet their quantitative advantage over classical finite-element methods (FEM) has remained limited to regular-grid domains. This work delivers the first systematic, large-scale head-to-head study between a minimalist single-Rm PIELM and FEM on four elliptic benchmarks of escalating difficulty with random collocation points: (i) a 2-D Poisson verification case, (ii) a 2-D heat-conduction problem with an internal cavity, (iii) a 2-D hyperbolic PDE featuring steep gradients, and (iv) the 3-D extension of (ii). More than 4 × 103 random hyper-parameter realisations are executed, spanning seven decades in training loss and error. For the two smooth 2-D benchmarks the PIELM attains sub-10−8 root-mean-square (RMS) errors while being at least an order of magnitude faster than equally accurate FEM. On the hyperbolic test it retains its speed edge and lowers the FEM error by one order of magnitude. In 3-D the PIELM reaches RMS values within a factor 4 of the FEM optimum yet requires only a fraction of the wall-time, revealing dimensionality limits but preserving favourable accuracy-per-second scaling. Statistical analysis uncovers an almost linear log–log correlation between the collocation residual and the RMS error, enabling a practical a-posteriori stopping criterion. Sensitivity sweeps identify the hidden-layer width M and the weight scale Rm as the dominant hyper-parameters, whereas the interior-to-boundary collocation ratio primarily governs stability. Error visualisations expose complementary failure modes between PIELM (local spikes) and FEM (global diffusion), suggesting the need for more robust collocation-points selection strategies. Overall, the evidence positions the single-Rm PIELM as a compelling alternative for fast, high-accuracy solutions of low- to moderate-dimensional, smooth PDEs, and charts a roadmap for overcoming the remaining challenges in high-dimensional and highly non-smooth regimes.
Keywords
Subject (DDC)
Event
Exhibition start date
Exhibition end date
Conference start date
Conference end date
Date of the last check
ISBN
ISSN
2169-3536
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Green
License
Citation
Sacchetti, A. (2026). When random features beat the mesh. Benchmarking physics-informed extreme learning machines against finite elements. IEEE Access, 1–12. https://doi.org/10.1109/access.2026.3668048