Performance Metrics for Multi-Objective Optimisation Algorithms Under Noise

2023/02/27 by Branke, Juergen
#FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2302.14179

Abstract

This paper discusses the challenge when evaluating multi-objective optimisation algorithms under noise, and argues that decision maker preferences need to be taken into account. It demonstrates that commonly used performance metrics are problematic when there is noise, and proposes two alternative performance metrics that capture selection error of the decision maker due to mis-estimating a solution's true fitness values.

Related

• Evaluating Noisy Optimisation Algorithms: First Hitting Time is Problematic
• Two Criteria for Performance Analysis of Optimization Algorithms
• Analyzing Evolutionary Optimization in Noisy Environments
• Analysis of Different Types of Regret in Continuous Noisy Optimization
• Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization