EUVIMEDEUVIMED entdecken
Crossref

Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation

Madison Cooley, Shandian Zhe, Robert M. Kirby, Varun Shankar

SIAM Journal on Scientific Computing · 31.08.2026 · 48 (4) · C1086-C1135

DOI: 10.1137/25m1773556 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 14.08.2026. Verfasst von Madison Cooley und 3 weiteren Autor:innen. Die Arbeit nennt 94 Literaturangaben. Gefördert von: Air Force Office of Scientific Research, Army Research Office.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present polynomial-augmented neural networks (PANNs), a novel machine learning architecture that combines deep neural networks (DNNs) with polynomial expansions. PANNs combine the strengths of DNNs (flexibility and efficiency in higher-dimensional approximation) with those of polynomial approximation (rapid convergence rates for smooth functions). To aid in both stable training and enhanced accuracy over a variety of problems, we present (1) a family of orthogonality constraints that impose mutual orthogonality between the polynomial and the DNN within a PANN; (2) a simple basis pruning approach to combat the curse of dimensionality introduced by the polynomial component; and (3) an adaptation of a polynomial preconditioning strategy to both DNNs and polynomials. We test the resulting architecture for its polynomial reproduction properties, ability to approximate both smooth functions and functions of limited smoothness, and as a method for the solution of partial differential equations (PDEs). Through these experiments, we demonstrate that PANNs offer superior approximation properties to DNNs for both regression and the numerical solution of PDEs while also offering enhanced accuracy over both polynomial and DNN-based regression (each) when regressing functions with limited smoothness.

Förderung

  • Air Force Office of Scientific Research
  • Army Research Office

Zitieren

APA

Cooley, M., Zhe, S., Kirby, R. M., & Shankar, V. (2026). Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation. SIAM Journal on Scientific Computing, 48(4), C1086-C1135. https://doi.org/10.1137/25m1773556

Vancouver

Cooley M, Zhe S, Kirby RM, Shankar V. Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation. SIAM Journal on Scientific Computing. 2026;48(4):C1086-C1135. doi:10.1137/25m1773556

BibTeX
@article{Cooley2026,
  author = {Cooley, Madison and Zhe, Shandian and Kirby, Robert M. and Shankar, Varun},
  title = {Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation},
  journal = {SIAM Journal on Scientific Computing},
  year = {2026},
  volume = {48},
  number = {4},
  pages = {C1086--C1135},
  doi = {10.1137/25m1773556}
}
Kostenlos starten →