A Unified Variational Principle for Reliable Machine Learning
Mathematics · 04.06.2026 · 14 (11) · 1994
DOI: 10.3390/math14111994 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 04.06.2026. Verfasst von Jose Manuel Velasco und 1 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish Minister of Science, Innovation, and Universities.
Abstract (Originalsprache)
Modern machine learning systems can achieve remarkable predictive performance. Nevertheless, in several fields, this is not enough to produce acceptable solutions as we need formal guarantees of robustness, fairness, and interpretability. Most existing approaches treat these properties separately or introduce them through external constraints, which makes their interaction difficult to analyze. In this work, we develop a unified variational perspective that incorporates these requirements directly into the learning objective. Concretely, we model learning as the minimization of a composite functional that combines predictive risk, regularization, and additional terms that capture robustness, fairness, and interpretability. This viewpoint allows us to study these properties within a single mathematical framework. Under standard assumptions, we prove the existence of minimizers and show that the resulting solutions are Pareto-optimal for the associated multi-objective problem. We illustrate the framework using examples based on adversarial and distributional robustness, statistical fairness criteria, and a notion of interpretability. The analysis points out the trade-offs that inevitably arise. We also examine statistical aspects of the proposed objective and show that classical generalization guarantees can still be obtained under appropriate conditions. The resulting framework provides a flexible basis for designing reliable learning systems.
Förderung
- Spanish Minister of Science, Innovation, and Universities
Zitieren
APA
Velasco, J. M., & Gonzalez-Perez, B. (2026). A Unified Variational Principle for Reliable Machine Learning. Mathematics, 14(11), 1994. https://doi.org/10.3390/math14111994
Vancouver
Velasco JM, Gonzalez-Perez B. A Unified Variational Principle for Reliable Machine Learning. Mathematics. 2026;14(11):1994. doi:10.3390/math14111994
BibTeX
@article{Velasco2026,
author = {Velasco, Jose Manuel and Gonzalez-Perez, Beatriz},
title = {A Unified Variational Principle for Reliable Machine Learning},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {11},
pages = {1994},
doi = {10.3390/math14111994}
}
EUVIMED