Log‐Linear Convergence and Divergence of the Scale‐Invariant (1+1)‐ES in Noisy Environments

Log‐Linear Convergence and Divergence of the Scale‐Invariant (1+1)‐ES in Noisy Environments

0.00 Avg rating0 Votes
Article ID: iaor20112039
Volume: 59
Issue: 3
Start Page Number: 425
End Page Number: 460
Publication Date: Mar 2011
Journal: Algorithmica
Authors: , ,
Keywords: evolution strategy
Abstract:

Noise is present in many real‐world continuous optimization problems. Stochastic search algorithms such as Evolution Strategies (ESs) have been proposed as effective search methods in such contexts. In this paper, we provide a mathematical analysis of the convergence of a (1+1)‐ES on unimodal spherical objective functions in the presence of noise. We prove for a multiplicative noise model that for a positive expected value of the noisy objective function, convergence or divergence happens depending on the infimum of the support of the noise. Moreover, we investigate convergence rates and show that log‐linear convergence is preserved in presence of noise. This result is a strong theoretical foundation of the robustness of ESs with respect to noise.

Reviews

Required fields are marked *. Your email address will not be published.