A Condition Number for Hamiltonian Monte Carlo

Autor:	Langmore, Ian, Dikovsky, Michael, Geraedts, Scott, Norgaard, Peter, Von Behren, Rob
Rok vydání:	2019
Předmět:	Statistics - Computation Mathematics - Statistics Theory Statistics - Methodology G.3
Druh dokumentu:	Working Paper
Popis:	Hamiltonian Monte Carlo is a popular sampling technique for smooth target densities. The scale lengths of the target have long been known to influence integration error and sampling efficiency. However, quantitative measures intrinsic to the target have been lacking. In this paper, we restrict attention to the multivariate Gaussian and the leapfrog integrator, and obtain a condition number corresponding to sampling efficiency. This number, based on the spectral and Schatten norms, quantifies the number of leapfrog steps needed to efficiently sample. We demonstrate its utility by using this condition number to analyze HMC preconditioning techniques. We also find the condition number of large inverse Wishart matrices, from which we derive burn-in heuristics. Comment: Significant changes: (i) Added connection to inverse Wishart ensemble, (ii) added estimation of kappa, (iii) checked and corrected proofs, (iv) re-wrote everything for clarity, (v) added authors
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1905.09813 Zobrazit plný text záznamu View this record from Arxiv