The variational method of moments
Journal of the Royal Statistical Society Series B: Statistical Methodology · 12.07.2023 · 85 (3) · 810-841
DOI: 10.1093/jrsssb/qkad025 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Royal Statistical Society Series B: Statistical Methodology, online erschienen am 27.04.2023. Verfasst von Andrew Bennett und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
The conditional moment problem is a powerful formulation for describing structural causal parameters in terms of observables, a prominent example being instrumental variable regression. We introduce a very general class of estimators called the variational method of moments (VMM), motivated by a variational minimax reformulation of optimally weighted generalized method of moments for finite sets of moments. VMM controls infinitely for many moments characterized by flexible function classes such as neural nets and kernel methods, while provably maintaining statistical efficiency unlike existing related minimax estimators. We also develop inference algorithms and demonstrate the empirical strengths of VMM estimation and inference in experiments.
Förderung
- National Science Foundation
Zitieren
APA
Bennett, A., & Kallus, N. (2023). The variational method of moments. Journal of the Royal Statistical Society Series B: Statistical Methodology, 85(3), 810-841. https://doi.org/10.1093/jrsssb/qkad025
Vancouver
Bennett A, Kallus N. The variational method of moments. Journal of the Royal Statistical Society Series B: Statistical Methodology. 2023;85(3):810-841. doi:10.1093/jrsssb/qkad025
BibTeX
@article{Bennett2023,
author = {Bennett, Andrew and Kallus, Nathan},
title = {The variational method of moments},
journal = {Journal of the Royal Statistical Society Series B: Statistical Methodology},
year = {2023},
volume = {85},
number = {3},
pages = {810--841},
doi = {10.1093/jrsssb/qkad025}
}
EUVIMED