Journal
EVOLUTIONARY COMPUTATION
Volume 30, Issue 1, Pages 27-50Publisher
MIT PRESS
DOI: 10.1162/evco_a_00295
Keywords
Evolution strategy; covariance matrix adaptation; linear convergence
Ask authors/readers for more resources
This article introduces the characteristics and performance of the class of algorithms called Hessian Estimation Evolution Strategies (HE-ESs), and provides two strong guarantees for the (1 + 4)-HE-ES algorithm: stability of covariance matrix update and linear convergence on all convex quadratic problems, regardless of the problem instance.
The class of algorithms called Hessian Estimation Evolution Strategies (HE-ESs) update the covariance matrix of their sampling distribution by directly estimating the curvature of the objective function. The approach is practically efficient, as attested by respectable performance on the BBOB testbed, even on rather irregular functions. In this article, we formally prove two strong guarantees for the (1 + 4)-HE-ES, a minimal elitist member of the family: stability of the covariance matrix update, and as a consequence, linear convergence on all convex quadratic problems at a rate that is independent of the problem instance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available