AI Paper Atlas

Research map / Optimization / Optimizers

Achieving High Accuracy with PINNs via Energy Natural Gradient Descent

Johannes Müller, Marius Zeinhofer

ICML 2023 · Optimization › Optimizers · approach: Natural gradient and Fisher approximations · 1 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 energy natural gradient descent instead of GDPINN for 2D Poisson equation · 2D Poisson equationrelative L2 error (median): 8.2 \cdot 10^{-3} -> 2.4\cdot 10^{-7}Improved
Use energy natural gradient descent instead of AdamPINN for 1D heat equation · 1D heat equationrelative L2 error (median): 1.0\cdot10^{-3} -> 6.3\cdot 10^{-6}Improved
Use energy natural gradient descent instead of BFGSPINN for 2D Poisson equation · 2D Poisson equationrelative L2 error (median): 4.4 \cdot 10^{-4} -> 2.4\cdot 10^{-7}Improved
Use Hilbert natural gradient instead of energy natural gradientPINN for 2D Poisson equation · 2D Poisson equationrelative L2 error (median): 2.4\cdot 10^{-7} -> 1.2Hurt
Use energy natural gradient descent instead of AdamDeep Ritz method for nonlinear elliptic equation · 1D nonlinear elliptic equation (deep Ritz)relative L2 error (median): 5.3\cdot10^{-5} -> 1.3\cdot10^{-8}Improved

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