Asymptotic properties of recursive particle maximum likelihood estimation
Using stochastic gradient search and the optimal filter derivative, it is possible to perform recursive (i.e., online) maximum likelihood estimation in a non-linear state-space model. As the optimal filter and its derivative are analytically intractable for such a model, they need to be approximated...
Autors principals: | Tadic, VZB, Doucet, A |
---|---|
Format: | Conference item |
Idioma: | English |
Publicat: |
IEEE
2019
|
Ítems similars
-
Asymptotic properties of recursive particle maximum likelihood estimation
per: Tadic, VZB, et al.
Publicat: (2020) -
Optimal recursive maximum likelihood estimation
Publicat: (2003) -
A distributed recursive maximum likelihood implementation for sensor registration
per: Kantas, N, et al.
Publicat: (2006) -
Bias of particle approximations to optimal filter derivative
per: Tadic, VZB, et al.
Publicat: (2021) -
Particle methods for maximum likelihood estimation in latent variable models
per: Johansen, A, et al.
Publicat: (2008)