English

Dynamic Subspace Estimation with Grassmannian Geodesics

Signal Processing 2023-03-28 v1 Computation

Abstract

Dynamic subspace estimation, or subspace tracking, is a fundamental problem in statistical signal processing and machine learning. This paper considers a geodesic model for time-varying subspaces. The natural objective function for this model is non-convex. We propose a novel algorithm for minimizing this objective and estimating the parameters of the model from data with Grassmannian-constrained optimization. We show that with this algorithm, the objective is monotonically non-increasing. We demonstrate the performance of this model and our algorithm on synthetic data, video data, and dynamic fMRI data.

Keywords

Cite

@article{arxiv.2303.14851,
  title  = {Dynamic Subspace Estimation with Grassmannian Geodesics},
  author = {Cameron J. Blocker and Haroon Raja and Jeffrey A. Fessler and Laura Balzano},
  journal= {arXiv preprint arXiv:2303.14851},
  year   = {2023}
}
R2 v1 2026-06-28T09:34:33.278Z