AI Paper Atlas

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

Deep Learning for Subspace Regression

Vladimir Fanaskov, Vladislav Trifonov, Alexander Rudikov, Ekaterina Muravleva, Ivan Oseledets

ICLR 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural operators for general geometries · 2 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
predict larger subspace than required (embedding, dim 10 -> 40) (ablation)subspace regression with L2 loss · D=2 elliptic eigenproblem, first 10 eigenvectorstest error (%): 30% -> 2%Improved
predict larger subspace (embedding) (ablation)subspace regression · D=2 elliptic eigenproblemgeneralisation gapImproved
use subspace regression with L1 loss instead of classical Riemannian interpolationeigenspace prediction · QM D=2 (a)relative error (%): 31.9% -> 0.65%Improved
use subspace loss instead of Z2-adjusted l2 eigenvector regressioneigenspace prediction · QM D=1relative error (%): 2.33% -> 0.09%Improved
use QR-free stochastic loss L2 instead of L1 as subspace size growssubspace regression · D=2 training timetraining timeImproved
use unstabilised L2 (normal equation) loss instead of L1 (ablation)subspace regression · D=3 elliptic eigenproblemrelative error (%): 24.77% -> 31.46% (size 6); fails at size 24Hurt
stabilise L2 with Cholesky-QR2 (ablation)subspace regression · D=3 elliptic eigenproblemrelative error (%): 31.46% -> 28.28% (size 6); 16.3% -> 7.4% (size 48)Improved
initialise LOBPCG with predicted subspaceLOBPCG · parametric eigenproblemsconvergence speed / relative error: 2 to 3 times faster; 2 orders lower errorImproved
train separate networks per eigenvector with Z2 l2 loss for higher-index eigenvectorseigenvector regression · D=2 elliptic eigenproblemtest errorHurt

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