This is a special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning". Algorithms have impact factor of 2.3 and SJR 3.7 and belongs to Q2 and Q3 according to JCR (Journal Citation Report) and SJR (SCImago Journal Rank Indicator). Normally, APC is charged before publishing, but potential authors can send inquiries for a possible discount or, in some exceptional cases, completely free publishing, to the guest editor Nikola Ivković. Please sand an inquiry as soon as you are considering doing research for this special issue.


Dear Colleagues,
This Special Issue focuses on swarm intelligence and evolutionary computation algorithms in general. Being stochastic, these algorithms generate better or worse solutions by chance. As a rule, in scientific research, the average performance based on the arithmetic mean is reported and analyzed. In practice, these algorithms can and should be executed multiple times (possibly in parallel) and the probability of obtaining peak performance solutions then increases arbitrarily to high certainty. Due to the parallelization trends of computing elements in recent decades, this became particularly practical. On the other hand, some application scenarios might require very high probabilities of obtaining a solution of at least some minimally acceptable quality and this is where bad-case performance matters.

Experimental studies of peak or bad-case performance of algorithms that previously showed state-of-the-art average performance are welcome. Large comparisons of peak performance or bad-case performance of swarm intelligence and evolutionary computation algorithms are welcome too, and theoretical findings concerning peak performance or bad-case performance are also welcome. Finally, parameter tuning procedures for peak performance or bad-case performance are welcome as well.

Dr. Nikola Ivković
Dr. Matej Črepinšek
Guest Editors

Additional info that might help
------------------------------
For Peak performance we recommend 10-percentile (0.1-quantile) or 25-percentile (Q1) and for bad-case performance 75-percentile(Q3) or 90-percentile (0.9-quantile).

1. Ivkovic, N.; Jakobovic, D.; Golub, M. Measuring Performance of Optimization Algorithms in Evolutionary Computation. Int. J. Mach. Learn. Comp. 2016, 6, 167–171.
https://doi.org/10.18178/ijmlc.2016.6.3.593
http://www.ijmlc.org/vol6/593-A27.pdf

2. Ivković N, Kudelić R, Črepinšek M. Probability and Certainty in the Performance of Evolutionary and Swarm Optimization Algorithms. Mathematics. 2022; 10(22):4364
https://doi.org/10.3390/math10224364
https://www.mdpi.com/2227-7390/10/22/4364