COCO: Performance Assessment

TL;DR

This paper introduces a performance assessment method for benchmarking numerical optimization algorithms using the COCO platform, focusing on runtime measured by function evaluations to reach quality targets, with a comprehensive discussion on target selection and result aggregation.

Contribution

It proposes an any-time performance assessment framework for optimization benchmarking based on runtime in function evaluations, enhancing the evaluation process within COCO.

Findings

Runtime is a meaningful performance measure.

The method allows for robust result aggregation.

Target value selection impacts assessment quality.

Abstract

We present an any-time performance assessment for benchmarking numerical optimization algorithms in a black-box scenario, applied within the COCO benchmarking platform. The performance assessment is based on runtimes measured in number of objective function evaluations to reach one or several quality indicator target values. We argue that runtime is the only available measure with a generic, meaningful, and quantitative interpretation. We discuss the choice of the target values, runlength-based targets, and the aggregation of results by using simulated restarts, averages, and empirical distribution functions.