Repository: Freie Universität Berlin, Math Department

Exact active subspace Metropolis-Hastings, with applications to the Lorenz-96 system

Schuster, I. and Constantine, P.G. and Sullivan, T.J. (2017) Exact active subspace Metropolis-Hastings, with applications to the Lorenz-96 system. SFB 1114 Preprint in arXiv:1712.02749 . pp. 1-10. (Unpublished)

[img]
Preview
PDF
446kB

Official URL: https://arxiv.org/abs/1712.02749

Abstract

We consider the application of active subspaces to inform a Metropolis-Hastings algorithm, thereby aggressively reducing the computational dimension of the sampling problem. We show that the original formulation, as proposed by Constantine, Kent, and Bui-Thanh (SIAM J. Sci. Comput., 38(5):A2779-A2805, 2016), possesses asymptotic bias. Using pseudo-marginal arguments, we develop an asymptotically unbiased variant. Our algorithm is applied to a synthetic multimodal target distribution as well as a Bayesian formulation of a parameter inference problem for a Lorenz-96 system.

Item Type:Article
Subjects:Mathematical and Computer Sciences > Mathematics > Applied Mathematics
ID Code:2162
Deposited By: Silvia Hoemke
Deposited On:13 Dec 2017 09:18
Last Modified:13 Dec 2017 09:18

Repository Staff Only: item control page