Convergence Analysis of the Hessian Estimation Evolution Strategy | MIT Press Journals & Magazine | IEEE Xplore

Convergence Analysis of the Hessian Estimation Evolution Strategy

;

Abstract:

The class of algorithms called Hessian Estimation Evolution Strategies (HE-ESs) update the covariance matrix of their sampling distribution by directly estimating the cur...Show More

Abstract:

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.
Published in: Evolutionary Computation ( Volume: 30, Issue: 1, 01 March 2022)
Page(s): 27 - 50
Date of Publication: 01 March 2022
Print ISSN: 1063-6560

Contact IEEE to Subscribe