Abstract

. I present a new Markov chain sampling method appropriate for distributions with isolated modes. Like the recently-developed method of "simulated tempering", the "tempered transition" method uses a series of distributions that interpolate between the distribution of interest and a distribution for which sampling is easier. The new method has the advantage that it does not require approximate values for the normalizing constants of these distributions, which are needed for simulated tempering, and can be tedious to estimate. Simulated tempering performs a random walk along the series of distributions used. In contrast, the tempered transitions of the new method move systematically from the desired distribution, to the easily-sampled distribution, and back to the desired distribution. This systematic movement avoids the inefficiency of a random walk, an advantage that unfortunately is cancelled by an increase in the number of interpolating distributions required. Because of this, the sa...

Citations

2802	Optimization by Simulated Annealing - Kirkpatrick, Gelati, et al. - 1983
448	Probabilistic inference using Markov chain Monte Carlo methods - Neal - 1993
141	CJ: Markov chain Monte Carlo maximum likelihood - Geyer
132	Annealing markov chain monte carlo with applications to ancestral inference - Geyer, Thompson - 1995
120	Simulated Tempering: a New Monte Carlo Scheme - Marinari, Parisi - 1992
29	Hybrid monte carlo - Duane, Kennedy, et al. - 1987
9	New Approach to Spin Glass Simulations - Berg, Celik - 1992
5	The Theory of Hybrid Stochastic Algorithms - Kennedy - 1990