KIT | KIT-Bibliothek | Impressum | Datenschutz

Calibrated Multivariate Regression with Localized PIT Mappings

Kock, Lucas; Rodrigues, G. S. ; Sisson, Scott A.; Klein, Nadja ORCID iD icon 1; Nott, David J.
1 Scientific Computing Center (SCC), Karlsruher Institut für Technologie (KIT)

Abstract:

Calibration ensures that predicted uncertainties align with observed uncertainties. While there is an extensive literature on recalibration methods for univariate probabilistic forecasts, work on calibration for multivariate forecasts is much more limited. This paper introduces a novel post-hoc recalibration approach that addresses multivariate calibration for potentially misspecified models. Our method involves constructing local mappings between vectors of marginal probability integral transform values and the space of observations, providing a flexible and model free solution applicable to continuous, discrete, and mixed responses. We present two versions of our approach: one uses K-nearest neighbors, and the other uses normalizing flows. Each method has its own strengths in different situations. We demonstrate the effectiveness of our approach on two real data applications: recalibrating a deep neural network's currency exchange rate forecast and improving a regression model for childhood malnutrition in India for which the multivariate response has both discrete and continuous components.


Zugehörige Institution(en) am KIT Karlsruher Institut für Technologie (KIT)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2024
Sprache Englisch
Identifikator KITopen-ID: 1000174378
HGF-Programm 46.21.02 (POF IV, LK 01) Cross-Domain ATMLs and Research Groups
Serie Methodology (stat.ME); Machine Learning (stat.ML)
Projektinformation ENP, 1. Förderabschnitt (DFG, DFG EIN, KL 3037/1-1)
Externe Relationen Siehe auch
Nachgewiesen in arXiv
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page