AI Paper Atlas

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

STDE++: Polynomial-Time Amortization for Linear Differential Operators

Zekun Shi, Zheyuan Hu, Min Lin, Kenji Kawaguchi

JMLR 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural operators for general geometries

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 JAX instead of PyTorch for stacked backward-mode SDGDBackward mode SDGD · Two-body Allen-Cahn, 100 Dtraining speed (it/s): 55.56 -> 40.63 (JAX slower at 100 D); about 15x speed-up overallImproved
parallelize the sampled-dimension loop of SDGD via HVP (ablation)Backward mode SDGD (JAX) · Two-body Allen-Cahn, 10K Dtraining speed (it/s): 29.85 -> 216.83Improved
use mixed-mode forward-over-backward AD instead of stacked backward (ablation)Parallelized backward mode SDGD · Two-body Allen-Cahn, 10K Dtraining speed (it/s): 216.83 vs 193.91No clear effect
replace parallelized SDGD with STDEParallelized backward mode SDGD · Two-body Allen-Cahn, 100K Dtraining speed (it/s): 29.24 -> 156.90Improved
replace parallelized SDGD with STDEParallelized backward mode SDGD · Two-body Allen-Cahn, 100K Dpeak memory (MB): 4931 -> 1073Improved
replace Forward Laplacian with STDE at high dimensionForward Laplacian · Two-body Allen-Cahn, 10K Dtraining speed (it/s): 32.15 -> 454.16Improved
replace Forward Laplacian with STDE at low dimensionForward Laplacian · Two-body Allen-Cahn, 100 Dtraining speed (it/s): 1974.50 -> 1035.09Hurt
replace original PyTorch SDGD with STDEBackward mode SDGD (PyTorch) · Two-body Allen-Cahn, 100K Dpeak memory (MB): 32777 -> 1073Improved
replace original PyTorch SDGD with STDEBackward mode SDGD (PyTorch) · Two-body Allen-Cahn, 100K Dtraining speed (it/s): 0.23 -> 156.90Improved
use STDE to scale to 1M dimensionsSTDE · Two-body Allen-Cahn, 1M Dtraining speed (it/s): OOM -> 13.61Improved

Later papers that compared with this method

1 later accepted paper reports STDE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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