Convergence of the Wang-Landau algorithm

Abstract

We analyze the convergence properties of the Wang-Landau algorithm. This sampling method belongs to the general class of adaptive importance sampling strategies which use the free energy along a chosen reaction coordinate as a bias. Such algorithms are very helpful to enhance the sampling properties of Markov Chain Monte Carlo algorithms, when the dynamics is metastable. We prove the convergence of the Wang-Landau algorithm and an associated central limit theorem.

This work is supported by the French National Research Agency under the grants ANR-09-BLAN-0216-01 (MEGAS) and ANR-08-BLAN-0218 (BigMC)