A Modern Genetic Optimization Method (2019)

Genetic Optimization Using Direction-Based Stochastic Search

Review of Multi-Offspring Improved Real-Coded Genetic Algorithm (MOIRCGA)

This is a review of a modern genetic algorithm called multi-offspring improved real-coded genetic algorithm (MOIRCGA). The original paper can be found here. The method used by this algorithm is, formally, called heuristical normal distribution and direction-based crosser (HNDDBX). This algorithm uses generates a direction-based candidate solution and modifies it with some parameterized random variable. The coded algorithm can be found on my github.

Short Overview

Genetic algorithms have been used for optimization since the 1960's. With the increased computational power of modern computers, genetic algorithms have gained attention for solving complex, non-linear objectives. For example, evolutionary strategies are used in neural architecture search, a technique for automating the design of neural networks.

This paper was mainly focused on constrained optimization. This includes linear and non-linear programming problems. Linear programming can be used to find exact solutions for a parameterized function with a set of constraints. However, problems can not always be defined as a parameterized function. For example, if the problem relying on computing some metric on a large dataset, has a large candidate…