A brief history of the introduction of generalized ensembles to Markov chain Monte Carlo simulations
- First Online:
- Cite this article as:
- Berg, B.A. Eur. Phys. J. Spec. Top. (2017) 226: 551. doi:10.1140/epjst/e2016-60236-2
- 24 Downloads
The most efficient weights for Markov chain Monte Carlo calculations of physical observables are not necessarily those of the canonical ensemble. Generalized ensembles, which do not exist in nature but can be simulated on computers, lead often to a much faster convergence. In particular, they have been used for simulations of first order phase transitions and for simulations of complex systems in which conflicting constraints lead to a rugged free energy landscape. Starting off with the Metropolis algorithm and Hastings’ extension, I present a minireview which focuses on the explosive use of generalized ensembles in the early 1990s. Illustrations are given, which range from spin models to peptides.