Towards Evolutionary Optimization Using the Ising Model

TL;DR

This paper introduces an Ising model-based evolutionary optimization algorithm designed to effectively find global minima in complex functions with many local minima, outperforming existing methods and showing potential for ensemble applications.

Contribution

The paper presents a novel optimization algorithm that leverages the Ising model to improve global minima detection in complex landscapes, advancing beyond prior techniques.

Findings

Outperforms comparable optimization methods in identifying global minima.

Creates stable local optima regions with high potential for improvement.

Shows promising applications to ensemble methods.

Abstract

In this paper, we study the problem of finding the global minima of a given function. Specifically, we consider complicated functions with numerous local minima, as is often the case for real-world data mining losses. We do so by applying a model from theoretical physics to create an Ising model-based evolutionary optimization algorithm. Our algorithm creates stable regions of local optima and a high potential for improvement between these regions. This enables the accurate identification of global minima, surpassing comparable methods, and has promising applications to ensembles.