Recorded Step Directional Mutation for Faster Convergence

TL;DR

This paper introduces directional mutation and recorded step strategies that significantly improve the convergence speed of evolutionary programming algorithms, especially on complex fitness landscapes, while maintaining their ability to handle multi-modal problems.

Contribution

The paper presents two novel meta-evolutionary strategies that enhance convergence speed and efficiency without requiring full covariance matrices, suitable for high-dimensional problems.

Findings

Accelerated convergence on complex fitness landscapes.

Maintained effectiveness on multi-modal problems.

Reduced storage requirements for high-dimensional problems.

Abstract

Two meta-evolutionary optimization strategies described in this paper accelerate the convergence of evolutionary programming algorithms while still retaining much of their ability to deal with multi-modal problems. The strategies, called directional mutation and recorded step in this paper, can operate independently but together they greatly enhance the ability of evolutionary programming algorithms to deal with fitness landscapes characterized by long narrow valleys. The directional mutation aspect of this combined method uses correlated meta-mutation but does not introduce a full covariance matrix. These new methods are thus much more economical in terms of storage for problems with high dimensionality. Additionally, directional mutation is rotationally invariant which is a substantial advantage over self-adaptive methods which use a single variance per coordinate for problems where the natural orientation of the problem is not oriented along the axes.