Newton-MR: Inexact Newton Method With Minimum Residual Sub-problem Solver
We consider a variant of inexact Newton Method, called Newton-MR, in which the least-squares sub-problems are solved approximately using Minimum Residual method. By construction, Newton-MR can be readily applied for unconstrained optimization of a class of non-convex problems known as invex, which s...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
29.09.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We consider a variant of inexact Newton Method, called Newton-MR, in which
the least-squares sub-problems are solved approximately using Minimum Residual
method. By construction, Newton-MR can be readily applied for unconstrained
optimization of a class of non-convex problems known as invex, which subsumes
convexity as a sub-class. For invex optimization, instead of the classical
Lipschitz continuity assumptions on gradient and Hessian, Newton-MR's global
convergence can be guaranteed under a weaker notion of joint regularity of
Hessian and gradient. We also obtain Newton-MR's problem-independent local
convergence to the set of minima. We show that fast local/global convergence
can be guaranteed under a novel inexactness condition, which, to our knowledge,
is much weaker than the prior related works. Numerical results demonstrate the
performance of Newton-MR as compared with several other Newton-type
alternatives on a few machine learning problems. |
---|---|
DOI: | 10.48550/arxiv.1810.00303 |