Continuously tempered Hamiltonian Monte Carlo
arXiv:1704.03338
Abstract
Hamiltonian Monte Carlo (HMC) is a powerful Markov chain Monte Carlo (MCMC) method for performing approximate inference in complex probabilistic models of continuous variables. In common with many MCMC methods, however, the standard HMC approach performs poorly in distributions with multiple isolated modes. We present a method for augmenting the Hamiltonian system with an extra continuous temperature control variable which allows the dynamic to bridge between sampling a complex target distribution and a simpler unimodal base distribution. This augmentation both helps improve mixing in multimodal targets and allows the normalisation constant of the target distribution to be estimated. The method is simple to implement within existing HMC code, requiring only a standard leapfrog integrator. We demonstrate experimentally that the method is competitive with annealed importance sampling and simulating tempering methods at sampling from challenging multimodal distributions and estimating their normalising constants.
arXiv comment16 pages, 7 figures
References in corpus (8)
- Auto-Encoding Variational Bayes
- Escaping free-energy minima
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Simulated Tempering: A New Monte Carlo Scheme
- Expectation Propagation for approximate Bayesian inference
- A Short History of Markov Chain Monte Carlo: Subjective Recollections from Incomplete Data
- Rényi Divergence Variational Inference
- Partition Functions from Rao-Blackwellized Tempered Sampling