IOHanalyzer: Performance Analysis for Iterative Optimization Heuristic
share
We propose IOHanalyzer, a new software for analyzing the empirical performance of iterative optimization heuristics (IOHs) such as local search algorithms, genetic and evolutionary algorithms, Bayesian optimization algorithms, and similar optimizers. Implemented in R and C++, IOHanalyzer is fully open source. It is available on CRAN and GitHub. IOHanalyzer provides a platform for analyzing and visualizing the performance of IOHs on real-valued, single-objective optimization tasks. It provides detailed statistics about the fixed-target running times and fixed-budget results of the benchmarked algorithms. Performance aggregation over several benchmark problems is also possible, for example in the form of empirical cumulative distribution functions. A key advantage of IOHanalyzer over other performance analysis packages is its highly interactive design, which allows the user to specify the performance measures, ranges, and granularity that are most useful for her experiments. It is designed to analyze not only performance traces, but also the evolution of dynamic state parameters. IOHanalyzer can directly process performance data from the main benchmarking platforms, including the COCO platform, Nevergrad, and our own IOHexperimenter. An R programming interface is provided for users preferring to have a finer control over the implemented functionalities.
READ FULL TEXT