AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features

Yulun Wu, Miguel Aguiar, Karl Henrik Johansson, Matthieu Barreau

ICLR 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use two-stage IFeF training instead of end-to-end joint optimization (ablation)IFeF-PINN · Helmholtz low-frequencyrelative L2 error: 0.0088 -> 0.0003Improved
use two-stage IFeF training instead of end-to-end (ablation)IFeF-PINN · Viscous Burgersrelative L2 error: 0.0049 -> 0.0024Improved
use two-stage IFeF training instead of end-to-end (ablation)IFeF-PINN · Helmholtz high-frequencyrelative L2 error: - -> 0.0156Improved
add RFF basis extension to iterative two-step training (ablation)IFeF-PINN · Convection high-frequency and Helmholtz high-frequencyrelative L2 errorImproved
add RFF basis extension to iterative two-step training (ablation)IFeF-PINN · Convection low-frequencyrelative L2 error: 1.4923 x 10^-2No clear effect
replace Vanilla PINN with IFeFVanilla PINN · Convection high-frequency (beta=200)relative L2 error: 0.9024 -> 0.0027Improved
replace Vanilla PINN with IFeFVanilla PINN · Convection-Diffusion multi-scalerelative L2 error: 0.0501 -> 0.0009Improved
add primal-dual weight balancing to IFeFIFeF · Helmholtz high-frequencyrelative L2 error: 0.0156 -> 0.0092Improved
add primal-dual weight balancing to IFeFIFeF · Viscous Burgersrelative L2 error: 0.0024 -> 0.0033Hurt
increase Fourier features D from 800 to 2400 (ablation)IFeF · Helmholtz high-frequencyrelative L2 error: 7.11 x 10^-2 -> 1.56 x 10^-2Improved
decrease sigma from 20 to 10 then to 0.2 (ablation)IFeF · Helmholtz high-frequencyrelative L2 error: 4.6 x 10^-3 -> 3.0 x 10^-3 -> 1.05 x 10^-1Mixed
vary D in 100 to 3000 (ablation)IFeF · Helmholtz low-frequencyrelative L2 error: 5.5 x 10^-4 -> 2.1 x 10^-4 -> 4.5 x 10^-4No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy