Efficient Bayesian inference on Grassmann manifolds leveraging Lagrangian Hamiltonian Monte Carlo
Information and Inference: A Journal of the IMA · 06.07.2026 · 15 (3)
DOI: 10.1093/imaiai/iaag030 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information and Inference: A Journal of the IMA, online erschienen am 04.08.2026. Verfasst von Anis Fradi und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben.
Abstract (Originalsprache)
We introduce a Bayesian framework for geodesic regression on Grassmann manifolds. Since a geodesic on the manifold is fully determined by its initial position and velocity, we reformulate the regression from function estimation to inferring these two initial conditions. We perform this inference via a Grassmann-specific Lagrangian Hamiltonian Monte Carlo method that exploits the manifold’s Riemannian geometry. Solving the associated Lagrangian dynamics reduces to following the geodesic flow, yielding an efficient inference procedure. We analyze the asymptotic properties of the resulting posterior, providing theoretical guarantees, and confirm the computational efficiency and accuracy of the approach experimentally on complex Bayesian modelling tasks.
Zitieren
APA
Fradi, A., Samir, C., & Joshi, S. H. (2026). Efficient Bayesian inference on Grassmann manifolds leveraging Lagrangian Hamiltonian Monte Carlo. Information and Inference: A Journal of the IMA, 15(3). https://doi.org/10.1093/imaiai/iaag030
Vancouver
Fradi A, Samir C, Joshi SH. Efficient Bayesian inference on Grassmann manifolds leveraging Lagrangian Hamiltonian Monte Carlo. Information and Inference: A Journal of the IMA. 2026;15(3). doi:10.1093/imaiai/iaag030
BibTeX
@article{Fradi2026,
author = {Fradi, Anis and Samir, Chafik and Joshi, Shantanu H},
title = {Efficient Bayesian inference on Grassmann manifolds leveraging Lagrangian Hamiltonian Monte Carlo},
journal = {Information and Inference: A Journal of the IMA},
year = {2026},
volume = {15},
number = {3},
doi = {10.1093/imaiai/iaag030}
}
EUVIMED