Axes that matter: PCA with a difference
Computational Finance
2025-03-19 v2
Abstract
We extend the scope of differential machine learning and introduce a new breed of supervised principal component analysis to reduce dimensionality of Derivatives problems. Applications include the specification and calibration of pricing models, the identification of regression features in least-square Monte-Carlo, and the pre-processing of simulated datasets for (differential) machine learning.
Keywords
Cite
@article{arxiv.2503.06707,
title = {Axes that matter: PCA with a difference},
author = {Brian Huge and Antoine Savine},
journal= {arXiv preprint arXiv:2503.06707},
year = {2025}
}
Comments
This article was first published in Risk in 2021