Population Control meets Doob's Martingale Theorems: the Noise-free Multimodal Case
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 mor...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2005.13970 |