Research

Paper

TESTING March 08, 2026

Learning embeddings of non-linear PDEs: the Burgers' equation

Authors

Pedro Tarancón-Álvarez, Leonid Sarieddine, Pavlos Protopapas, Raul Jimenez

Abstract

Embeddings provide low-dimensional representations that organize complex function spaces and support generalization. They provide a geometric representation that supports efficient retrieval, comparison, and generalization. In this work we generalize the concept to Physics Informed Neural Networks. We present a method to construct solution embedding spaces of nonlinear partial differential equations using a multi-head setup, and extract non-degenerate information from them using principal component analysis (PCA). We test this method by applying it to viscous Burgers' equation, which is solved simultaneously for a family of initial conditions and values of the viscosity. A shared network body learns a latent embedding of the solution space, while linear heads map this embedding to individual realizations. By enforcing orthogonality constraints on the heads, we obtain a principal-component decomposition of the latent space that is robust to training degeneracies and admits a direct physical interpretation. The obtained components for Burgers' equation exhibit rapid saturation, indicating that a small number of latent modes captures the dominant features of the dynamics.

Metadata

arXiv ID: 2603.07812
Provider: ARXIV
Primary Category: math.AP
Published: 2026-03-08
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.07812v1</id>\n    <title>Learning embeddings of non-linear PDEs: the Burgers' equation</title>\n    <updated>2026-03-08T21:32:31Z</updated>\n    <link href='https://arxiv.org/abs/2603.07812v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.07812v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Embeddings provide low-dimensional representations that organize complex function spaces and support generalization. They provide a geometric representation that supports efficient retrieval, comparison, and generalization. In this work we generalize the concept to Physics Informed Neural Networks. We present a method to construct solution embedding spaces of nonlinear partial differential equations using a multi-head setup, and extract non-degenerate information from them using principal component analysis (PCA). We test this method by applying it to viscous Burgers' equation, which is solved simultaneously for a family of initial conditions and values of the viscosity. A shared network body learns a latent embedding of the solution space, while linear heads map this embedding to individual realizations. By enforcing orthogonality constraints on the heads, we obtain a principal-component decomposition of the latent space that is robust to training degeneracies and admits a direct physical interpretation. The obtained components for Burgers' equation exhibit rapid saturation, indicating that a small number of latent modes captures the dominant features of the dynamics.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.AP'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-08T21:32:31Z</published>\n    <arxiv:comment>Accepted to ICLR2026</arxiv:comment>\n    <arxiv:primary_category term='math.AP'/>\n    <author>\n      <name>Pedro Tarancón-Álvarez</name>\n    </author>\n    <author>\n      <name>Leonid Sarieddine</name>\n    </author>\n    <author>\n      <name>Pavlos Protopapas</name>\n    </author>\n    <author>\n      <name>Raul Jimenez</name>\n    </author>\n  </entry>"
}