Research

Paper

AI LLM March 06, 2026

Kinetic-based regularization: Learning spatial derivatives and PDE applications

Authors

Abhisek Ganguly, Santosh Ansumali, Sauro Succi

Abstract

Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regularization (KBR), a localized multidimensional kernel regression method with a single trainable parameter, to learn spatial derivatives with provable second-order accuracy in 1D. Two derivative-learning schemes are proposed: an explicit scheme based on the closed-form prediction expressions, and an implicit scheme that solves a perturbed linear system at the points of interest. The fully localized formulation enables efficient, noise-adaptive derivative estimation without requiring global system solving or heuristic smoothing. Both approaches exhibit quadratic convergence, matching second-order finite difference for clean data, along with a possible high-dimensional formulation. Preliminary results show that coupling KBR with conservative solvers enables stable shock capture in 1D hyperbolic PDEs, acting as a step towards solving PDEs on irregular point clouds in higher dimensions while preserving conservation laws.

Metadata

arXiv ID: 2603.06380
Provider: ARXIV
Primary Category: math.NA
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.06380v1</id>\n    <title>Kinetic-based regularization: Learning spatial derivatives and PDE applications</title>\n    <updated>2026-03-06T15:32:27Z</updated>\n    <link href='https://arxiv.org/abs/2603.06380v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.06380v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regularization (KBR), a localized multidimensional kernel regression method with a single trainable parameter, to learn spatial derivatives with provable second-order accuracy in 1D. Two derivative-learning schemes are proposed: an explicit scheme based on the closed-form prediction expressions, and an implicit scheme that solves a perturbed linear system at the points of interest. The fully localized formulation enables efficient, noise-adaptive derivative estimation without requiring global system solving or heuristic smoothing. Both approaches exhibit quadratic convergence, matching second-order finite difference for clean data, along with a possible high-dimensional formulation. Preliminary results show that coupling KBR with conservative solvers enables stable shock capture in 1D hyperbolic PDEs, acting as a step towards solving PDEs on irregular point clouds in higher dimensions while preserving conservation laws.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.NA'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-06T15:32:27Z</published>\n    <arxiv:comment>Published as a conference paper at ICLR 2026 Workshop AI and PDE</arxiv:comment>\n    <arxiv:primary_category term='math.NA'/>\n    <author>\n      <name>Abhisek Ganguly</name>\n    </author>\n    <author>\n      <name>Santosh Ansumali</name>\n    </author>\n    <author>\n      <name>Sauro Succi</name>\n    </author>\n  </entry>"
}