TY - JOUR
T1 - Geodesic Lagrangian Monte Carlo over the space of positive definite matrices
T2 - with application to Bayesian spectral density estimation
AU - Holbrook, Andrew
AU - Lan, Shiwei
AU - Vandenberg-Rodes, Alexander
AU - Shahbaba, Babak
N1 - Funding Information:
AH is supported by NIH grant [T32 AG000096]. SL is supported by the Defense Advanced Research Projects Agency (DARPA) funded program Enabling Quantification of Uncertainty in Physical Systems (EQUiPS), contract W911NF-15-2-0121. AV and BS are supported by National Institutes of Health [grant R01-AI107034] and National Science Foundation [grant DMS-1622490].
Publisher Copyright:
© 2017 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2018/3/24
Y1 - 2018/3/24
N2 - We present geodesic Lagrangian Monte Carlo, an extension of Hamiltonian Monte Carlo for sampling from posterior distributions defined on general Riemannian manifolds. We apply this new algorithm to Bayesian inference on symmetric or Hermitian positive definite (PD) matrices. To do so, we exploit the Riemannian structure induced by Cartan's canonical metric. The geodesics that correspond to this metric are available in closed-form and–within the context of Lagrangian Monte Carlo–provide a principled way to travel around the space of PD matrices. Our method improves Bayesian inference on such matrices by allowing for a broad range of priors, so we are not limited to conjugate priors only. In the context of spectral density estimation, we use the (non-conjugate) complex reference prior as an example modelling option made available by the algorithm. Results based on simulated and real-world multivariate time series are presented in this context, and future directions are outlined.
AB - We present geodesic Lagrangian Monte Carlo, an extension of Hamiltonian Monte Carlo for sampling from posterior distributions defined on general Riemannian manifolds. We apply this new algorithm to Bayesian inference on symmetric or Hermitian positive definite (PD) matrices. To do so, we exploit the Riemannian structure induced by Cartan's canonical metric. The geodesics that correspond to this metric are available in closed-form and–within the context of Lagrangian Monte Carlo–provide a principled way to travel around the space of PD matrices. Our method improves Bayesian inference on such matrices by allowing for a broad range of priors, so we are not limited to conjugate priors only. In the context of spectral density estimation, we use the (non-conjugate) complex reference prior as an example modelling option made available by the algorithm. Results based on simulated and real-world multivariate time series are presented in this context, and future directions are outlined.
KW - HMC
KW - Riemannian geometry
KW - spectral analysis
UR - http://www.scopus.com/inward/record.url?scp=85039161063&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85039161063&partnerID=8YFLogxK
U2 - 10.1080/00949655.2017.1416470
DO - 10.1080/00949655.2017.1416470
M3 - Article
AN - SCOPUS:85039161063
SN - 0094-9655
VL - 88
SP - 982
EP - 1002
JO - Journal of Statistical Computation and Simulation
JF - Journal of Statistical Computation and Simulation
IS - 5
ER -