AI Paper Atlas

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

Meta-Auto-Decoder for Solving Parametric Partial Differential Equations

Xiang Huang, Zhanhong Ye, Hongsheng Liu, Shi Bei Ji, Zidong Wang, Kang Yang, Yang Li, Min Wang, Haotian CHU, Fan Yu, Bei Hua, Lei Chen and 1 more

NeurIPS 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural PDE solvers · 16 citations (OpenAlex)

Read the paper

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 MAD-LM instead of training from scratchBurgers' equation · Burgers' equationconvergence iterations: about 1200 iterations -> about 200 iterationsImproved
Use MAD-LM instead of Transfer-LearningBurgers' equation · Burgers' equationconvergence iterations: about 1200 iterations -> about 200 iterationsImproved
Fine-tune model weights along with the latent vector rather than optimizing only the latent vector (ablation)MAD · Burgers' equationmean L2 error: 0.028 -> 0.013Improved
Fine-tune model weights along with the latent vector rather than optimizing only the latent vector (ablation)MAD · Maxwell's equationsL2 error: 0.037 -> 0.030Improved
Fine-tune model weights along with the latent vector rather than optimizing only the latent vector (ablation)MAD · Laplace's equationL2 error: 0.0015 -> 0.0005Improved
Increase the number of pre-training samples from 10 to 50 (ablation)MAD-L · Burgers' equationmean L2 error: 0.365 -> 0.046Improved
Increase the number of pre-training samples from 10 to 50 (ablation)MAD-LM · Burgers' equationmean L2 error: 0.015 -> 0.013Improved
Increase the number of pre-training samples from 50 to 100 (ablation)PI-DeepONet · Burgers' equationmean L2 error: 0.247 -> 0.217Improved
Increase the number of pre-training samples from 200 to 300 (ablation)PI-DeepONet · Burgers' equationmean L2 error: 0.169 -> 0.181Hurt
Increase latent-vector size (ablation)MAD-L · Burgers' equationmean L2 errorMixed
Increase latent-vector size (ablation)MAD-LM · Burgers' equationmean L2 errorNo clear effect
Use MAD-LM instead of PI-DeepONetMaxwell's equations · Maxwell's equationsmean L2 error: 0.672 -> 0.028Improved

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