AI Paper Atlas

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

Harmonized Cone for Feasible and Non-conflict Directions in Training Physics-Informed Neural Networks

Dohyun Bu, Yujung Byun, Jong-Seok Lee

ICLR 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training

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
add HARMONIC projection to keep update inside H (ablation)ConFIG · Poisson2d-Crelative L2 error: 0.6856 -> 0.0094Improved
add HARMONIC projection to keep update inside H (ablation)ReLoBRaLo · Poisson2d-Crelative L2 error: 0.6602 -> 0.0948Improved
add HARMONIC projection to keep update inside H (ablation)CAGrad · Poisson2d-Crelative L2 error: 0.6969 -> 0.0312Improved
add HARMONIC projection to keep update inside H (ablation)ConFIG · Wave1d-Crelative L2 error: 0.0668 -> 0.0407Improved
add HARMONIC projection to keep update inside H (ablation)ConFIG · Volterra1drelative L2 error: 0.0018 -> 0.0064Hurt
add HARMONIC projection to keep update inside H (ablation)ReLoBRaLo · Volterra1drelative L2 error: 0.0002 -> 0.0179Hurt
add HARMONIC projection to keep update inside H (ablation)ReLoBRaLo · HInvrelative L2 error: 1.5999 -> 0.0467Improved
add HARMONIC projection to keep update inside H (ablation)ConFIG · HInvrelative L2 error: 0.0466 -> 0.0558Hurt
HARMONIC vs best baselines on Poisson2d-CHARMONIC · Poisson2d-Crelative L2 error: 0.2847 -> 0.0214Improved
HARMONIC vs ConFIG on Wave1d-CHARMONIC · Wave1d-Crelative L2 error: 0.0668 -> 0.0655No 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