Interpreting evolutionary algorithms as approximate MCMC yields DME, which samples a global target distribution without weight updates and is more sample-efficient on problems needing many samples
The work interprets several evolutionary algorithms as approximate Markov Chain Monte Carlo (MCMC) and, on that basis, introduces Distribution Matching Evolutionary Algorithms (DME), a class of search methods that sample from a global target distribution without updating model weights and that empirically shows higher sample efficiency than existing methods on problems requiring many samples to find a solution.