AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver

Pietro Sittoni, Emanuele Zangrando, Angelo Alberto Casulli, Nicola Guglielmi, Francesco Tudisco

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 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
use Neural-HSS instead of FNOFNO · Heat equation (1D)test error: 8 x 10^-3 -> 3 x 10^-3Improved
use Neural-HSS instead of FNOFNO · Poisson equation (2D)test error: 7 x 10^-6 -> 7 x 10^-8Improved
use Neural-HSS instead of FNOFNO · Burgers' equation (1D)test error: 0.26 -> 0.12Improved
use Neural-HSS instead of ResNetResNet · Gray-Scott forward (2D)test error: 0.273 -> 0.294Hurt
use Neural-HSS instead of ResNetResNet · Gray-Scott inverse (2D)test error: 0.193 -> 0.203Hurt
use Neural-HSS instead of FNOFNO · Navier-Stokes forward (2D)test error: 0.483 -> 0.123Improved
use Neural-HSS instead of FNOFNO · Navier-Stokes inverse (2D)test error: 0.19 -> 0.208Hurt
train Neural-HSS with 16 samples vs FNO with 64 samplesNeural-HSS · Poisson 3D data efficiencytest error: 16 samples matches FNO at 64 and ResNet at 128Improved
use full-rank lifting and projection (ablation)Neural-HSS · Burgers' equation (1D)test errorImproved
shift Burgers' equation toward elliptic (smaller beta)Neural-HSS · Modified Burgers' equationtrajectory test lossImproved
vary rank r, outer rank r_out and levels t over grid (ablation)Neural-HSS · Gray-Scotttest errorNo clear effect
use non-rectangular or mixed-BC domainsNeural-HSS · Poisson L-shape domaintest error: 2 x 10^-1 -> 2 x 10^-2Improved

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