HAMSI: A Parallel Incremental Optimization Algorithm Using Quadratic Approximations for Solving Partially Separable Problems
Published in arXiv (Cornell University) • Sep 5, 2015
NobleIDNI7P64W76R19S35
Authors:,,
Kamer Kaya
Figen Öztoprak
Ş. İlker Birbil
Abstract
We propose HAMSI (Hessian Approximated Multiple Subsets Iteration), which is a provably convergent, second order incremental algorithm for solving large-scale partially separable optimization problems. The algorithm is based on a local quadratic approximation, and hence, allows incorporating curvatu...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!