- Title
- Variational State and Parameter Estimation
- Creator
- Courts, Jarrad; Hendriks, Johannes; Wills, Adrian; Schön, Thomas B.; Ninness, Brett
- Relation
- 19th IFAC Symposium on System Identification (SYSID). Proceedings of 19th IFAC Symposium on System Identification (SYSID), Volume 54 (Padova, Italy 13-16 July, 2021) p. 732-737
- Publisher Link
- http://dx.doi.org/10.1016/j.ifacol.2021.08.448
- Publisher
- Elsevier
- Resource Type
- conference paper
- Date
- 2021
- Description
- This paper considers the problem of computing Bayesian estimates of both states and model parameters for nonlinear state-space models. Generally, this problem does not have a tractable solution and approximations must be utilised. In this work, a variational approach is used to provide an assumed density which approximates the desired, intractable, distribution. The approach is deterministic and results in an optimisation problem of a standard form. Due to the parametrisation of the assumed density selected first and second order derivatives are readily available which allows for efficient solutions. The proposed method is compared against state-of-the-art Hamiltonian Monte Carlo in two numerical examples.
- Subject
- Bayesian inference; system identification; variational inference; nonlinear models; parameter estimation
- Identifier
- http://hdl.handle.net/1959.13/1450786
- Identifier
- uon:44022
- Identifier
- ISSN:2405-8963
- Rights
- © 2021 The Authors. This is an open access article under the CC BY-NC-ND license.
- Language
- eng
- Full Text
- Reviewed
- Hits: 873
- Visitors: 886
- Downloads: 22
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | ATTACHMENT02 | Publisher version (open access) | 624 KB | Adobe Acrobat PDF | View Details Download |