AI Paper Atlas

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

PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks

Kevin von Bargen, Hamid Ebrahimy, Tim Römer

NeurIPS 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes PINNeval, an evaluation standard that decomposes PINN training into four components (domain-importance adaptation, loss balancing, architecture, optimization) and evaluates them jointly rather than in isolation.

Problem

Existing PINN benchmarks study the components of the training pipeline in isolation, and the studies set the supervision/setup in inconsistent ways, making method comparisons hard.

Approach

Systematically divides the PINN training pipeline into four components and provides a unified evaluation standard that assesses them together rather than separately.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use two-stage MLP pipeline (SOAP then SSBroyden2, float64) instead of single-stage PirateNet-SOAPPINN training pipeline · demanding PDE benchmarksmedian relative L2 error and runtimeImproved
add quasi-Newton SSBroyden2 stage to MLP at same precision (ablation)MLP under SOAP · Heat PDErelative L2 error: error reduced by up to a factor of 1.7 x 10^4Improved
use float64 precision alone (ablation)MLP under SOAP · PINN benchmarksrelative L2 errorNo clear effect
replace PirateNet with MLP under SOAP alone (ablation)PINN with SOAP · PINN benchmarksrelative L2 errorHurt
use PINNpipe efficient implementation with LAS instead of jaxpi with Random-RGinzburg-Landau benchmark · Ginzburg-Landauruntime (minutes): 746.0 -> 519.2Improved
adaptive domain-importance methods (RAD, R3, vRBA) instead of random resampling under SOAP (ablation)PINN pipeline with SOAP · Wave, Heat, KdV, Rayleigh-Taylorrelative L2 errorHurt
use LAS adaptive sampling instead of Random-R (ablation)PINN pipeline with SOAP · Wave and Heatrelative L2 errorNo clear effect
random resampling versus adaptive sampling (ablation)PINN pipeline with SOAP · KdV and Rayleigh-Taylorrelative L2 errorImproved
use GradNorm-based loss balancing (ablation)PINN pipeline with Random-R · nine PDE benchmarksmedian relative L2 error: best on 5 of 9 benchmarksImproved
fixed-weight loss baseline (ablation)PINN pipeline with Random-R · KS, AC, KdVmedian relative L2 errorImproved
use SoftAdapt loss balancing (ablation)PINN pipeline · Wave and KSrelative L2 errorHurt
use GradNorm-MTL loss balancing (ablation)PINN pipeline · KdVrelative L2 errorHurt

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