Iterative Hessian Sketch with momentum

Date

2019

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
2
views
33
downloads

Citation Stats

Series

Abstract

We propose a novel randomized linear least squares solver which is an improvement of Iterative Hessian Sketch and randomized preconditioning. In the proposed Momentum-IHS technique (M-IHS), Heavy Ball Method is used to accelerate the convergence of iterations. It is shown that for any full rank data matrix, rate of convergence depends on the ratio between the feature size and the sketch size. Unlike the Conjugate Gradient technique, the rate of convergence is unaffected by either the condition number or the eigenvalue spectrum of the data matrix. As demonstrated over many examples, the proposed M-IHS provides compatible performance with the state of the art randomized preconditioning methods such as LSRN or Blendenpik and yet, it provides a completely different perspective in the area of iterative solvers which can pave the way for future developments.

Source Title

Proceedings of the 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019

Publisher

Institute of Electrical and Electronics Engineers Inc.

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)

Language

English