Theory of estimation-of-distribution algorithms
Carsten Witt · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2019
Summary Runtime analysis for simple univariate EDAs Identified similarities to and differences from simple EAs Genetic drift a major obstacle Sensitive to parameters (phase transitions) Robust to noise Significance-based EDAs as novel theory-driven approach Future work Combinatorial problems Multivariate EDAs Classification of problems w. r. t. appropriateness for EAs/EDAs.