Population Control meets Doob's Martingale Theorems: the Noise-free Multimodal Case

Cauwet, Marie-Liesse, Teytaud, Olivier

arXiv.org Artificial Intelligence 

We study a test-based population size adaptation (TBPSA) method, inspired from population control, in the noise-free multimodal case. In the noisy setting, TBPSA usually recommends, at the end of the run, the center of the Gaussian as an approximation of the optimum. We show that combined with a more naive recommendation, namely recommending the visited point which had the best fitness value so far, TBPSA is also powerful in the noise-free multimodal context. We demonstrate this experimentally and explore this mechanism theoretically: we prove that TBPSA is able to escape plateaus with probability one in spite of the fact that it can converge to local minima. This leads to an algorithm effective in the multimodal setting without resorting to a random restart from scratch.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found