Overcoming Complexity Catastrophe: An Algorithm for Beneficial Far-Reaching Adaptation under High Complexity
Neural and Evolutionary Computing
2021-05-11 v1 Adaptation and Self-Organizing Systems
Abstract
In his seminal work with NK algorithms, Kauffman noted that fitness outcomes from algorithms navigating an NK landscape show a sharp decline at high complexity arising from pervasive interdependence among problem dimensions. This phenomenon - where complexity effects dominate (Darwinian) adaptation efforts - is called complexity catastrophe. We present an algorithm - incremental change taking turns (ICTT) - that finds distant configurations having fitness superior to that reported in extant research, under high complexity. Thus, complexity catastrophe is not inevitable: a series of incremental changes can lead to excellent outcomes.
Cite
@article{arxiv.2105.04311,
title = {Overcoming Complexity Catastrophe: An Algorithm for Beneficial Far-Reaching Adaptation under High Complexity},
author = {Sasanka Sekhar Chanda and Sai Yayavaram},
journal= {arXiv preprint arXiv:2105.04311},
year = {2021}
}
Comments
10 pages, 5 Figures