Bayesian joint state and parameter tracking in autoregressive models

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

We address the problem of online Bayesian state and parameter tracking in autoregressive (AR) models with time-varying process noise variance. The involved marginalization and expectation integrals cannot be analytically solved. Moreover, the online tracking constraint makes sampling and batch learning methods unsuitable for this problem. We propose a hybrid variational message passing algorithm that robustly tracks the time-varying dynamics of the latent states, AR coefficients and process noise variance. Since message passing in a factor graph is a highly modular inference approach, the proposed methods easily extend to other non-stationary dynamic modeling problems.
Originele taal-2Engels
TitelConference on Learning for Dynamics and Control
UitgeverijProceedings of Machine Learning Research
Aantal pagina's10
StatusGepubliceerd - jun 2020
Evenement2nd Annual Conference on Learning for Dynamics and Control - UC Berkeley, Berkeley, Verenigde Staten van Amerika
Duur: 11 jun 202012 jun 2020
Congresnummer: 2
https://l4dc.org

Congres

Congres2nd Annual Conference on Learning for Dynamics and Control
Verkorte titelL4DC
LandVerenigde Staten van Amerika
StadBerkeley
Periode11/06/2012/06/20
Internet adres

Vingerafdruk Duik in de onderzoeksthema's van 'Bayesian joint state and parameter tracking in autoregressive models'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Senoz, I., Podusenko, A., Kouw, W. M., & de Vries, A. B. (2020). Bayesian joint state and parameter tracking in autoregressive models. In Conference on Learning for Dynamics and Control [120] Proceedings of Machine Learning Research. https://openreview.net/pdf?id=uaYWeSAp5a5