A Divide-and-Conquer Algorithm for the Bidiagonal SVD

The authors present a stable and efficient divide-and-conquer algorithm for computing the singular value decomposition (SVD) of a lower bidiagonal matrix. Previous divide-and-conquer algorithms all suffer from a potential loss of orthogonality among the computed singular vectors unless extended precision arithmetic is used. A generalization that computes the SVD of a lower banded matrix is also presented.