Black-Box Inference for Non-Linear Latent Force Models
Abstract
Latent force models are systems whereby there is a mechanistic model describing the dynamics of the system state, with some unknown forcing term that is approximated with a Gaussian process. If such dynamics are non-linear, it can be difficult to estimate the posterior state and forcing term jointly, particularly when there are system parameters that also need estimating. This paper uses black-box variational inference to jointly estimate the posterior, designing a multivariate extension to local inverse autoregressive flows as a flexible approximater of the system. We compare estimates on systems where the posterior is known, demonstrating the effectiveness of the approximation, and apply to problems with non-linear dynamics, multi-output systems and models with non-Gaussian likelihoods.
Cite
@article{arxiv.1906.09199,
title = {Black-Box Inference for Non-Linear Latent Force Models},
author = {Wil O. C. Ward and Tom Ryder and Dennis Prangle and Mauricio A. Álvarez},
journal= {arXiv preprint arXiv:1906.09199},
year = {2019}
}
Comments
13 pages plus references and supplementary