AI Paper Atlas

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

Improving physics-informed neural networks with meta-learned optimization

Alex Bihlo

JMLR 2024 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 14 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
replace Adam with meta-learned optimizerPINN · 1D linear advectiontraining loss and point-wise error: more than 10 times smallerImproved
replace Adam with meta-learned optimizerPINN · 1D linear advectionepochs to reach loss: 500 epochs vs 3000 epochsImproved
replace Adam with meta-learned optimizerPINN · 2D Poisson equationtraining loss and point-wise errorImproved
replace Adam with meta-learned optimizerPINN · KdV equationepochs to reach loss: 200 epochs vs 1000 epochsImproved
meta-train optimizer on ensemble of initial conditions (transfer to unseen initial condition)meta-learned optimizer on PINN · KdV equation, unseen initial condition k=2, phi=-pi/4training loss: 200 epochs vs 1000 epochsImproved
replace Adam with meta-learned optimizer trained on Burgers equationPINN · Burgers equationtraining loss and errorImproved
use optimizer meta-trained on linear advection equation instead of AdamPINN · Burgers equation (cross-equation transfer)training lossMixed

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