AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds

Nathanael Tepakbong, Hanyu HU, Chengyu Liu, Xiang ZHOU

ICML 2026 · Optimization › Implicit bias and generalization · approach: Gradient flow and mean-field dynamics · 0 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
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Poisson PDEL2 abs error: 1.333 -> 0.761Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Poisson PDEL2 rel error: 0.322 -> 0.1184Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Poisson PDEH1 abs error: 12.42 -> 7.822Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Schrödinger-type PDEL2 abs error: 0.475 -> 0.073Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Schrödinger-type PDEL2 rel error: 0.624 -> 0.096Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Schrödinger-type PDEH1 abs error: 2.893 -> 1.043Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Schrödinger-type PDEH1 rel error: 0.512 -> 0.185Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Mean Escape Time PDEL2 abs error: 16.56 -> 1.755Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Mean Escape Time PDEL2 rel error: 1.007 -> 0.107Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Mean Escape Time PDEH1 rel error: 1.002 -> 0.395Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Committor PDEL2 abs error: 1.028 -> 0.791Improved
add Feynman-Kac Monte Carlo supervision to the PINN loss (FK-PINN)PINN · Committor PDEL2 rel error: 0.839 -> 0.030Improved

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