AI Paper Atlas

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

Finite Expression Method for Solving High-Dimensional Partial Differential Equations

Senwei Liang, Haizhao Yang

JMLR 2025 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural PDE solvers

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 FEX-derived structured parametrization (FEX-NN) instead of vanilla NNNN-based PDE solver · Poisson, conservation law, Schrodingerrelative L2 errorImproved
increase binary tree depth (2, 3, 4, 6, 8) when exact solution is unreachable (ablation)FEX · Poisson equation (square operator excluded)relative L2 errorImproved
replace genetic programming with RL controller for operator searchFEX · High-dimensional PDEsrelative L2 errorImproved
add FEX-guided exp(v(x)) postprocessing iterationNN eigenvalue solver · Eigenvalue w=|x|^2, d=10relative eigenvalue error: up to 20% -> close to zeroImproved
use FEX instead of NN for non-analytic eigenfunction (quartic potential)eigenvalue solver · delta=0.1, d=10-18smallest eigenvalueImproved

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