Efficiency of the Wang-Landau algorithm: a simple test case

DOI10.1093/AMRX/ABU003MaRDI QIDQ2927897zbMATH OpenOpenAlexFDO

Authors Benjamin Jourdain, Estelle Kuhn, Tony Lelièvre, Gabriel Stoltz, Gersende Fort

Publication date 5 November 2014

Published in AMRX. Applied Mathematics Research eXpress (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1310.6550

zbMATH Keywords

adaptive importance samplingcomputational statistical physicsMarkov chain Monte CarloMetropolis-Hastings algorithmnumerical resultWang-Landau algorithm

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Applications of statistics to physics (62P35) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

Abstract: We analyze the efficiency of the Wang-Landau algorithm to sample a multimodal distribution on a prototypical simple test case. We show that the exit time from a metastable state is much smaller for the Wang Landau dynamics than for the original standard Metropolis-Hastings algorithm, in some asymptotic regime. Our results are confirmed by numerical experiments on a more realistic test case.

Review text

The Wang-Landau algorithm is an adaptive importance Markov chain Monte Carlo (MCMC) technique based on a single trajectory interacting with its own past. The authors analyze the efficiency of this algorithm in escaping metastable states. Analytic results are presented for a toy model with only three states (two metastable states and one intermediate state which is visited with a low probability). Numerical results are discussed for a 2D-model from computational statistical physics. It is shown that in these examples the exit times from metastable states are much smaller for the Wang-Landau algorithm than for the standard Metropolis-Hastings algorithm.

Recommendations

• Convergence of the Wang-Landau algorithm
• The Wang-Landau algorithm in general state spaces: applications and convergence analysis
• Convergence and refinement of the Wang-Landau algorithm
• Wang-Landau algorithm: an adapted random walk to boost convergence
• The Wang-Landau algorithm reaches the flat histogram criterion in finite time

Cited in

(15)

• Hypocoercivity in metastable settings and kinetic simulated annealing
• Convergence and efficiency of adaptive importance sampling techniques with partial biasing
• Wang-Landau sampling: saving CPU time
• The Wang-Landau algorithm reaches the flat histogram criterion in finite time
• Dynamics of the Wang–Landau algorithm and complexity of rare events for the three-dimensional bimodal Ising spin glass
• The Wang-Landau algorithm in general state spaces: applications and convergence analysis
• ON THE WANG–LANDAU METHOD USING THE N-FOLD WAY
• Self-healing umbrella sampling: convergence and efficiency
• Convergence of the Wang-Landau algorithm
• Metropolized randomized maximum likelihood for improved sampling from multimodal distributions
• NUMERICAL COMPARISON OF WANG–LANDAU SAMPLING AND PARALLEL TEMPERING FOR MET-ENKEPHALIN
• A Generalized Wang–Landau Algorithm for Monte Carlo Computation
• Wang-Landau simulations with non-flat distributions
• Performance of Wang-Landau algorithm in continuous spin models and a case study: Modified XY-model
• Wang-Landau algorithm: an adapted random walk to boost convergence

This page was built for publication: Efficiency of the Wang-Landau algorithm: a simple test case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2927897)