AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm

Shizheng Wen, Mingyuan chi, Tianwei Yu, Ben Moseley, Mike Yan Michelis, Pu Ren, Hao Sun, Siddhartha Mishra

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 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
replace FEniCS (CPU) with TensorMesh (CPU) on mixed-BC Poisson circle domainTensorMesh · Mixed-BC Poisson circle (6K nodes, CPU)end-to-end time (ms): 7{,}000 -> 133 (~52x)Improved
replace FEniCS (CPU) with TensorMesh (CPU) on mixed-BC Poisson boomerang domainTensorMesh · Mixed-BC Poisson boomerang (14.8K nodes, CPU)end-to-end time (ms): 5{,}600 -> 317 (~18x)Improved
use TensorMesh instead of JAX-FEM for topology optimization optimization loopTensorOpt · 2D cantilever beam topology optimizationtime (s): 28.51 s -> 7.77 s (3.7x)Improved
use TensorMesh instead of JAX-FEM for topology optimization setupTensorOpt · 2D cantilever beam topology optimizationsetup time (s): 2.62 s -> 0.58 s (4.5x)Improved
use analytic-shape-gradient Galerkin loss (TensorPils) instead of Deep RitzNeural PDE solver · Poisson checkerboard K=8relative L2 error (%): 10.60 -> 10.05Improved
use TensorPils instead of PINN strong-form lossNeural PDE solver · Poisson checkerboard K=8relative L2 error (%): 34.77 -> 10.05Improved
use TensorPils instead of PINN for training throughput (LBFGS)Neural PDE solver · Poisson checkerboardtraining speed (it/s): 1.0 -> 99.7Improved
use physics-informed TensorPils instead of data-driven training with same GNN (OOD wave)GNN operator · Wave operator learning OODrelative L2 error: 0.230 -> 0.090Improved
use TensorPils instead of data-driven training in-distribution (wave)GNN operator · Wave operator learning IDrelative L2 error: 0.089 -> 0.085No clear effect
use TensorPils instead of PI-DeepONet (AC OOD)operator learning · Allen-Cahn operator learning OODrelative L2 error: 8.536 -> 0.083Improved
use TensorPils loss instead of PINN loss on unstructured meshes (forward pass)loss evaluation · unstructured triangular meshesforward loss time: roughly 4--6$\times$ fasterImproved
use TensorMesh GPU instead of second-best FEniCS for Poisson solvingTensorMesh · Poisson, up to 1e6 DoFsruntime: 3 times speedupImproved

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