Abstract
We propose a novel approach to improve multi-objective evolutionary algorithms by modifying crossover operations. Our approach uses a modifiable cross distribution and virtual point to rebalance the probability distribution of all crossover options. This design reduces runtime for typical pseudo-Boolean functions. Experiments and analysis show our approach effectively optimizes bi-objective problems COCZ and LOTZ in Θ(n) time during crossover, outperforming conventional crossover multi-objective evolutionary algorithms (C-MOEA) which require O(n log n) steps. For the tri-objective problem Hierarchical-COCZ, our approach guarantees an expected runtime of Θ(n2 log n), while C-MOEA needs at least Ω(n2 log n) and at most O(n2 log2 n) steps.
Keywords
- Search: S: Evolutionary computation
- Machine Learning: ML: Evolutionary learning
