EUVIMEDEUVIMED entdecken
Crossref

On the Uncertainty Quantification Ability of Tabular Foundation Models

Tyler R. Johnson, Kian Ben-Jacob, Nima Negarandeh, Oriol Vendrell-Gallart, Ramin Bostanabad

Computing in Science & Engineering · 2026-07 · 28 (3) · 75-85

DOI: 10.1109/mcse.2026.3701626 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computing in Science & Engineering, 2026-07. Verfasst von Tyler R. Johnson und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 12 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation models (FMs) have achieved substantial success in generalizing across tasks without problem-specific training or fine-tuning. However, many critical applications in mechanics and computational science require not only accurate predictions but also reliable uncertainty quantification (UQ). Herein we investigate the UQ capabilities of tabular FMs in regression tasks through a comprehensive empirical study comparing tabular Prior-Data Fitted Networks (TabPFN) against Gaussian processes (GPs). We systematically evaluate these two methods across a host of regression problems with varying complexity and dataset sizes. We use a default setting to build all of the GPs for a fair comparison against TabPFN v2.5. Our findings highlight an important tradeoff between explicit and learned priors: While TabPFN achieves highly competitive performance for complex, high-dimensional problems with sufficient data, GPs often provide superior predictive accuracy and UQ in data-scarce settings and when the chosen kernel constitutes a good prior Our results can be reproduced from https://github.com/kianswarehouse/GPvsPFN.

Zitieren

APA

Johnson, T. R., Ben-Jacob, K., Negarandeh, N., Vendrell-Gallart, O., & Bostanabad, R. (2026). On the Uncertainty Quantification Ability of Tabular Foundation Models. Computing in Science & Engineering, 28(3), 75-85. https://doi.org/10.1109/mcse.2026.3701626

Vancouver

Johnson TR, Ben-Jacob K, Negarandeh N, Vendrell-Gallart O, Bostanabad R. On the Uncertainty Quantification Ability of Tabular Foundation Models. Computing in Science & Engineering. 2026;28(3):75-85. doi:10.1109/mcse.2026.3701626

BibTeX
@article{Johnson2026,
  author = {Johnson, Tyler R. and Ben-Jacob, Kian and Negarandeh, Nima and Vendrell-Gallart, Oriol and Bostanabad, Ramin},
  title = {On the Uncertainty Quantification Ability of Tabular Foundation Models},
  journal = {Computing in Science & Engineering},
  year = {2026},
  volume = {28},
  number = {3},
  pages = {75--85},
  doi = {10.1109/mcse.2026.3701626}
}
Kostenlos starten →