A Nearly-Black-Box Online Algorithm for Joint Parameter and State Estimation in Temporal Models
Abstract
Online joint parameter and state estimation is a core problem for temporal models.Most existing methods are either restricted to a particular class of models (e.g., the Storvik filter) or computationally expensive (e.g., particle MCMC). We propose a novel nearly-black-box algorithm, the Assumed Parameter Filter (APF), a hybrid of particle filtering for state variables and assumed density filtering for parameter variables.It has the following advantages:(a) it is online and computationally efficient;(b) it is applicable to both discrete and continuous parameter spaces with arbitrary transition dynamics.On a variety of toy and real models, APF generates more accurate results within a fixed computation budget compared to several standard algorithms from the literature.
Cite
Text
Erol et al. "A Nearly-Black-Box Online Algorithm for Joint Parameter and State Estimation in Temporal Models." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.10836Markdown
[Erol et al. "A Nearly-Black-Box Online Algorithm for Joint Parameter and State Estimation in Temporal Models." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/erol2017aaai-nearly/) doi:10.1609/AAAI.V31I1.10836BibTeX
@inproceedings{erol2017aaai-nearly,
title = {{A Nearly-Black-Box Online Algorithm for Joint Parameter and State Estimation in Temporal Models}},
author = {Erol, Yusuf Bugra and Wu, Yi and Li, Lei and Russell, Stuart},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2017},
pages = {1861-1869},
doi = {10.1609/AAAI.V31I1.10836},
url = {https://mlanthology.org/aaai/2017/erol2017aaai-nearly/}
}