Theoretical Guarantees for the Subspace-Constrained Tyler's Estimator

arXiv:2403.18658v1 Announce Type: cross
Abstract: This work analyzes the subspace-constrained Tyler's estimator (STE) designed for recovering a low-dimensional subspace within a dataset that may be highly corrupted with outliers. It assumes a weak inlier-outlier model and allows the fraction of inliers to be smaller than a fraction that leads to computational hardness of the robust subspace recovery problem. It shows that in this setting, if the initialization of STE, which is an iterative algorithm, satisfies a certain condition, then STE …

abstract arxiv computational dataset estimator leads low math.st outlier outliers stat.ml stat.th tyler type work