Practical Inexact Proximal Quasi-Newton Method with Global Complexity Analysis
Machine Learning
2015-07-15 v4 Optimization and Control
Machine Learning
Abstract
Recently several methods were proposed for sparse optimization which make careful use of second-order information [10, 28, 16, 3] to improve local convergence rates. These methods construct a composite quadratic approximation using Hessian information, optimize this approximation using a first-order method, such as coordinate descent and employ a line search to ensure sufficient descent. Here we propose a general framework, which includes slightly modified versions of existing algorithms and also a new algorithm, which uses limited memory BFGS Hessian approximations, and provide a novel global convergence rate analysis, which covers methods that solve subproblems via coordinate descent.
Cite
@article{arxiv.1311.6547,
title = {Practical Inexact Proximal Quasi-Newton Method with Global Complexity Analysis},
author = {Katya Scheinberg and Xiaocheng Tang},
journal= {arXiv preprint arXiv:1311.6547},
year = {2015}
}