Orthogonal iterations on Structured Pencils

Abstract

We present a class of fast subspace tracking algorithms based on orthogonal iterations for structured matrices/pencils that can be represented as small rank perturbations of unitary matrices. The algorithms rely upon an updated data sparse factorization -- named LFR factorization -- using orthogonal Hessenberg matrices. These new subspace trackers reach a complexity of only $O(n{k}^2)$ operations per time update, where $n$ and $k$ are the size of the matrix and of the small rank perturbation, respectively.