A Hybrid Algorithm for Metaheuristic Optimization

2019/05/26 by Sujit Pramod Khanna, Khanna, Sujit Pramod, Alexander Ororbia II +1
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Neural and Evolutionary Computing (cs.NE) #cs.AI #cs.LG #cs.MA #cs.NE

paper · pdf · doi:10.48550/arxiv.1906.02010

10 pages, 5 figures

arxiv created 2019/05/26 · arxiv updated 2019/06/06

Abstract

We propose a novel, flexible algorithm for combining together metaheuristicoptimizers for non-convex optimization problems. Our approach treatsthe constituent optimizers as a team of complex agents that communicateinformation amongst each other at various intervals during the simulationprocess. The information produced by each individual agent can be combinedin various ways via higher-level operators. In our experiments on keybenchmark functions, we investigate how the performance of our algorithmvaries with respect to several of its key modifiable properties. Finally,we apply our proposed algorithm to classification problems involving theoptimization of support-vector machine classifiers.

Related

• A survey of meta-heuristic methods for optimization problems
• METAFOR: A Hybrid Metaheuristics Software Framework for Single-Objective Continuous Optimization Problems
• Meta-Learning Parameterized First-Order Optimizers using Differentiable Convex Optimization
• Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach
• A socio-physics based hybrid metaheuristic for solving complex non-convex constrained optimization problems