Evals is not enough: why we should report wall-clock time

Citation

Woodward J, Brownlee A & Johnson C (2016) Evals is not enough: why we should report wall-clock time. In: Friedrich T (ed.) GECCO '16 Companion Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion. GECCO 2016: Genetic and Evolutionary Computation Conference, Denver, CO, USA, 20.07.2016-24.07.2016. New York: ACM, pp. 1157-1158. https://doi.org/10.1145/2908961.2931695

Abstract
Have you ever noticed that your car never achieves the fuel economy claimed by the manufacturer? Does this seem unfair? Unscientific? Would you like the same situation to occur in Genetic Improvement? Comparison will always be difficult [9], however, guidelines have been discussed [3, 5, 4]. With two GP [8] approaches, comparing the number of evaluations of the fitness function is reasonably fair. This means you are comparing the GP systems, and not how well they are implemented, how fast the language is. However, the situation with GI [6, 1] is unique. With GI we will typically compare systems which are applied to the same application written in the same language (i.e. a GI systems targeted at Java, may not even be applied to C). Thus, wall-clock time becomes more relevant. Thus, this paper asks if reporting number of evaluations is enough, or if wall-clock time is also important, particularly in the context of GI. It argues that reporting time is even more important when doing GI when compared to traditional GP.

Keywords
Genetic Improvement (GI); Genetic Programming (GP)

People

Dr Sandy Brownlee

Senior Lecturer in Computing Science, Computing Science and Mathematics - Division