Algorithms for estimation of low-rank matrices with triple Kronecker structured singular vectors

We consider the problem of estimating the singular vectors of low-rank signal matrices buried in noise in the setting where the singular vectors are assumed to be Kronecker products of three unknown vectors. We propose several algorithms for estimating such singular vectors, which explicitly exploit the Kronecker structure of the underlying vectors. We demonstrate improved estimation accuracy and improved clutter suppression in MIMO STAP applications, using the newly proposed singular vector estimates.