Black-box optimization benchmarking of prototype optimization with evolved improvement steps for noiseless function testbed
Jiřı́ Kubalı́k · 2009
This paper presents benchmarking of a stochastic local search algorithm called Prototype Optimization with Evolved Improvement Steps (POEMS) on the noise-free BBOB 2009 testbed. Experiments for 2, 3, 5, 10 and 20 D were done, where D denotes the search space dimension. The maximum number of function evaluations is chosen as 105 x D. Experimental results show that POEMS performs best on all separable functions and the attractive sector function. It works also quite well on multi-modal functions with lower dimensions. On the other hand, the algorithm fails to solve functions with high conditioning.