AI Paper Atlas

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

Overcoming PINNs Failure Modes In High Dimension With Low-Rank Fourier Sum

Natan Kaminsky, Daniel Freedman, Kira Radinsky

ICML 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
replace neural network with low-rank separable Fourier sum and analytic lossPINN · Convection PDErMAE: 0.0059 -> 8.2E-06 (vs PINN FP64)Improved
replace neural network with LoRFSPINN · Reaction PDErMAE: 0.0092 -> 0.0002 (vs PINNMamba)Improved
replace neural network with LoRFSPINN · Wave PDErMAE: 0.0080 -> 0.0033 (vs PINN FP64)Improved
use LoRFS in high dimensions instead of PINN FP64 or PINNMambaPINN solvers · High-dimensional WaverRMSE: 0.8584 -> 5.9E-05 (vs PINN FP64)Improved
use LoRFS in high dimensionsPINN solvers · High-dimensional ReactionrRMSE: 1.0001 -> 0.0082 (vs PINN FP64)Improved
use analytic differentiation of Fourier series instead of stochastic or autodiff high-order estimatorsbiharmonic solver · Biharmonic equationrMAE: 7.8E-03 -> 4.6E-04 (vs Forward Laplacian)Improved
use stochastic Monte Carlo estimators (HTE, STDE) instead of deterministic Forward Laplacianbiharmonic solver · Biharmonic equationrMAE: 7.8E-03 -> 1.97E-02 / 2.29E-02Hurt
increase rank s and Fourier degree K beyond a threshold (ablation)LoRFS · Reaction PDE sensitivityrRMSE: threshold K > 5 and s > 5No clear effect
use a slower PINN architecture (PINNMamba) within a fixed 1 hour budget in high dimensionPINNMamba · High-dimensional PDEsrRMSEHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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