Analysis of Surrogate-Assisted Information-Geometric Optimization Algorithms

Surrogate functions are often employed to reduce the number of objective function evaluations in a continuous optimization. However, their effects have seldom been investigated theoretically. This paper analyzes effect surrogate information-geometric optimization (IGO) framework, which includes as an algorithm instance variant covariance matrix adaptation evolution strategy—a widely used solver for black-box We derive sufficient condition on parameter update IGO algorithms point descent direction expected over search distribution. The is expressed terms three measures correlation between and function. Our result constitutes partial justification use algorithms.