Modeling the Drift Function in Stochastic Differential Equations using Reduced Rank Gaussian Processes
(2018) 18th IFAC Symposium on System Identification In IFAC-PapersOnLine 51(15). p.778-783- Abstract
- In this paper, we propose a Gaussian process-based nonlinear, time-varying drift model for stochastic differential equations. In particular, we combine eigenfunction expansion of the Gaussian process’ covariance kernel in the spatial input variables with spectral decomposition in the time domain to obtain a reduced rank state space representation of the drift model, which avoids the growing complexity (with respect to time) of the full Gaussian process solution. The proposed approach is evaluated on two nonlinear benchmark problems, the Bouc Wen and the cascaded tanks systems.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/99964b06-fdc1-45fb-9de5-18880e62d8a6
- author
- Hostettler, Roland ; Tronarp, Filip LU and Särkkä, Simo
- publishing date
- 2018
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- host publication
- 18th IFAC Symposium on System Identification SYSID 2018
- series title
- IFAC-PapersOnLine
- editor
- Rojas, Christian
- volume
- 51
- issue
- 15
- pages
- 778 - 783
- publisher
- Elsevier
- conference name
- 18th IFAC Symposium on System Identification
- conference location
- Stockholm, Sweden
- conference dates
- 2018-07-09 - 2018-07-11
- external identifiers
-
- scopus:85054443004
- ISSN
- 2405-8963
- 2405-8971
- DOI
- 10.1016/j.ifacol.2018.09.137
- language
- English
- LU publication?
- no
- id
- 99964b06-fdc1-45fb-9de5-18880e62d8a6
- date added to LUP
- 2023-08-21 02:11:48
- date last changed
- 2024-06-14 05:56:44
@inproceedings{99964b06-fdc1-45fb-9de5-18880e62d8a6, abstract = {{In this paper, we propose a Gaussian process-based nonlinear, time-varying drift model for stochastic differential equations. In particular, we combine eigenfunction expansion of the Gaussian process’ covariance kernel in the spatial input variables with spectral decomposition in the time domain to obtain a reduced rank state space representation of the drift model, which avoids the growing complexity (with respect to time) of the full Gaussian process solution. The proposed approach is evaluated on two nonlinear benchmark problems, the Bouc Wen and the cascaded tanks systems.}}, author = {{Hostettler, Roland and Tronarp, Filip and Särkkä, Simo}}, booktitle = {{18th IFAC Symposium on System Identification SYSID 2018}}, editor = {{Rojas, Christian}}, issn = {{2405-8963}}, language = {{eng}}, number = {{15}}, pages = {{778--783}}, publisher = {{Elsevier}}, series = {{IFAC-PapersOnLine}}, title = {{Modeling the Drift Function in Stochastic Differential Equations using Reduced Rank Gaussian Processes}}, url = {{http://dx.doi.org/10.1016/j.ifacol.2018.09.137}}, doi = {{10.1016/j.ifacol.2018.09.137}}, volume = {{51}}, year = {{2018}}, }