On Least Squares Approximations of Shapley Values and Applications to Interpretable Machine Learning
Foundations · 11.05.2026 · 6 (2) · 18
DOI: 10.3390/foundations6020018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Foundations, online erschienen am 11.05.2026. Verfasst von Tim Pollmann und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The Shapley value is the predominant point-valued solution concept in cooperative game theory and has recently become a foundational method in interpretable machine learning. In this domain, a prevailing strategy for circumventing the computational intractability of exact Shapley values is to approximate them via a weighted least squares optimization framework. In this paper, we investigate an existing algorithmic framework for weighted least squares Shapley approximation, assessing its feasibility for feature attribution. Methodologically, we conduct a theoretical variance analysis within a Monte Carlo sampling framework, investigate an approach for sample reuse across strata, and establish a relation to Unbiased KernelSHAP. Our analysis reveals three main findings: (i) a structural equivalence between least squares sampling and Unbiased KernelSHAP; (ii) the non-zero covariance between sampled coalitions introduced by reusing samples across strata in one of the existing least squares-based approaches; and (iii) the absence of a universally optimal sampling strategy across tasks. We validate these results empirically on several cooperative games and practical machine learning problems.
Zitieren
APA
Pollmann, T., & Staudacher, J. (2026). On Least Squares Approximations of Shapley Values and Applications to Interpretable Machine Learning. Foundations, 6(2), 18. https://doi.org/10.3390/foundations6020018
Vancouver
Pollmann T, Staudacher J. On Least Squares Approximations of Shapley Values and Applications to Interpretable Machine Learning. Foundations. 2026;6(2):18. doi:10.3390/foundations6020018
BibTeX
@article{Pollmann2026,
author = {Pollmann, Tim and Staudacher, Jochen},
title = {On Least Squares Approximations of Shapley Values and Applications to Interpretable Machine Learning},
journal = {Foundations},
year = {2026},
volume = {6},
number = {2},
pages = {18},
doi = {10.3390/foundations6020018}
}
EUVIMED