AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks

Jules Berman, Benjamin Peherstorfer

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 4 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 PINN with RSNG (s=800)RSNG · Allen-CahnL2 relative error: 6.85e-02 -> 1.66e-05Improved
Replace Causal PINN with RSNG (s=800)RSNG · Allen-CahnL2 relative error: 3.84e-04 -> 1.66e-05Improved
Replace Causal PINN with RSNG (s=800)RSNG · Burgers'L2 relative error: 5.19e-04 -> 6.07e-05Improved
Replace Causal PINN with RSNG (s=125)RSNG · Burgers'training time (s): 23027 -> 188Improved
Reduce sparsity s from 800 to 150 in RSNG (ablation)RSNG · Allen-Cahntraining time (s): 776 -> 63Improved
Reduce sparsity s from 800 to 150 in RSNG (ablation)RSNG · Allen-CahnL2 relative error: 1.66e-05 -> 5.34e-05Hurt
Reduce sparsity s from 800 to 125 in RSNG (ablation)RSNG · Burgers'L2 relative error: 6.07e-05 -> 2.05e-04Hurt
Use sparse randomized updates (s below p) instead of dense updates in 7-layer network (ablation)Neural Galerkin · Allen-Cahn, Burgers', Vlasovrelative error: 2--3x lower errorImproved
Use 7-layer network with sparse updates (s equal to 3-layer p) instead of 3-layer dense updates at equal cost (ablation)Neural Galerkin · Allen-Cahn, Burgers', Vlasovrelative errorImproved
Use RSNG instead of dense direct solverNeural Galerkin · Burgers'runtime at comparable errorImproved
Use RSNG instead of dense iterative solverNeural Galerkin · Burgers'runtime at comparable errorImproved
Periodically refit network from random initialization (dense iterative solver) (ablation)Neural Galerkin · Burgers'relative error vs runtimeMixed

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