Ian Langmore
Published 2019-05-23Version 1
Hamiltonian Monte Carlo is a popular sampling technique for smooth target densities. The scale lengths of the target have long been believed to influence sampling efficiency, but quantitative measures intrinsic to the target have been lacking. In this paper, we restrict attention to multivariate Gaussian targets, and obtain a condition number corresponding to sampling efficiency. This number, based on a mix of spectral and Schatten norms, quantifies the number of leapfrog steps needed to efficiently sample. We demonstrate its utility by using the condition number to analyze preconditioning techniques for HMC.
On the convergence of dynamic implementations of Hamiltonian Monte Carlo and No U-Turn Samplers
Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?
Hamiltonian Monte Carlo with Energy Conserving Subsampling
![QR code for arXiv:1905.09813 [stat.CO]](http://oss.arxitics.com/images/favicon.svg)