| 1. |
- Jones, Elizabeth A., et al.
(author)
-
How to Operationalise Collaborative Research
- 2018
-
In: Issues and Concepts in Historical Ecology. - Cambridge : Cambridge University Press. - 9781108420983 - 9781108355780 ; , s. 240-271
-
Conference paper (peer-reviewed)
|
|
| 2. |
- Wigren, Anna, et al.
(author)
-
Improving the particle filter in high dimensions using conjugate artificial process noise
- 2018
-
In: 18th IFAC Symposium on System IdentificationSYSID 2018 Proceedings. - : Elsevier BV. ; , s. 670-675
-
Conference paper (peer-reviewed)abstract
- The particle filter is one of the most successful methods for state inference and identification of general non-linear and non-Gaussian models. However, standard particle filters suffer from degeneracy of the particle weights, in particular for high-dimensional problems. We propose a method for improving the performance of the particle filter for certain challenging state space models, with implications for high-dimensional inference. First we approximate the model by adding artificial process noise in an additional state update, then we design a proposal that combines the standard and the locally optimal proposal. This results in a bias-variance trade-off, where adding more noise reduces the variance of the estimate but increases the model bias. The performance of the proposed method is empirically evaluated on a linear-Gaussian state space model and on the non-linear Lorenz'96 model. For both models we observe a significant improvement in performance over the standard particle filter.
|
|
| 3. |
- Wigren, Anna, et al.
(author)
-
Parameter elimination in particle Gibbs sampling
- 2019
-
In: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019). - : NEURAL INFORMATION PROCESSING SYSTEMS (NIPS).
-
Conference paper (peer-reviewed)abstract
- Bayesian inference in state-space models is challenging due to high-dimensional state trajectories. A viable approach is particle Markov chain Monte Carlo, combining MCMC and sequential Monte Carlo to form "exact approximations" to otherwise intractable MCMC methods. The performance of the approximation is limited to that of the exact method. We focus on particle Gibbs and particle Gibbs with ancestor sampling, improving their performance beyond that of the underlying Gibbs sampler (which they approximate) by marginalizing out one or more parameters. This is possible when the parameter prior is conjugate to the complete data likelihood. Marginalization yields a non-Markovian model for inference, but we show that, in contrast to the general case, this method still scales linearly in time. While marginalization can be cumbersome to implement, recent advances in probabilistic programming have enabled its automation. We demonstrate how the marginalized methods are viable as efficient inference backends in probabilistic programming, and demonstrate with examples in ecology and epidemiology.
|
|
