arXiv cs.NE
· Papers
Why can genetic algorithms work in high-dimensional search spaces?
arXiv:2606.30619v1 Announce Type: cross Abstract: We show that the effective dynamics of the elitist $(1+M)$ genetic algorithm is, in the limit of small mutations, clipped gradient descent on the loss in the presence of anisotropic Gaussian white noise. In expectation, therefore, a simple mutation-selection genetic alg