Evolutionary Monte Carlo: Applications to C-p model sampling and change point problem

Motivated by the success of genetic algorithms and simulated annealing in h ard optimization problems, the authors propose a new Markov chain Monte Car lo (MCMC) algorithm called an evolutionary Monte Carlo algorithm. This algo rithm has incorporated several attractive features of genetic algorithms an d simulated annealing into the framework of MCMC. It works by simulating a population of Markov chains in parallel, where a different temperature is a ttached to each chain. The population is updated by mutation (Metropolis up date), crossover (partial state swapping) and exchange operators (full stat e swapping). The algorithm is illustrated through examples of C-p-based mod el selection and change-point identification. The numerical results and the extensive comparisons show that evolutionary Monte Carlo is a promising ap proach for simulation and optimization.