Numerous studies have shown that advanced estimation of distribution algorithms (EDAs) often discover spurious (unnecessary) dependencies. Nonetheless, only little prior work exists that would study the effects of spurious dependencies on EDA performance. This paper examines the effects of spurious dependencies on the performance and scalability of EDAs with the main focus on EDAs with marginal product models and the onemax problem. A theoretical model is proposed to analyze the effects of spurious dependencies on the population sizing in EDAs and the theory is verified with experiments. The effects of spurious dependencies on the number of generations are studied empirically. The effects of replacement strategies on the performance of EDAs with spurious linkage are also investigated.
展开▼
