[Forum SIS] Webinar of Guillaume Kon Kam King @Unimib

[Bernardo Nipoti]

Dear all,

We are glad to announce the next DEMS Statistics Webinar, organized by the
Department of Economics, Management and Statistics (DEMS) of the University
of Milano - Bicocca.

Speaker: Guillaume Kon Kam King, Université Paris-Saclay, INRAE, France

https://sites.google.com/site/guillaumekonkamking

Wednesday, December 9th, 2020, time 13.00 (CET).

Link to attend the event:

https://unimib.webex.com/unimib/onstage/g.php?MTID=e301e542cc5af6058f9b5599ba8a5930b

*******************************************************

Title:

Exact inference for a class of non-linear hidden Markov models on general
state spaces

Abstract:

Filtering hidden Markov models, or sequential Bayesian inference on the
hidden state of a signal, is analytically tractable only for a handful of
models. Examples are finite-dimensional state space models and linear
Gaussian systems (Baum-Welch and Kalman filters). Recently,
Papaspiliopoulos et al. ([1], [2])⁠ proposed a principled approach for
extending the realm of analytically tractable models, exploiting a duality
relation between the hidden process and an auxiliary process. Then, the
solution of the filtering problem consists in a finite mixture of
distributions. We study the computational effort required to implement this
strategy for two parametric and nonparametric models: the
Cox-Ingersoll-Ross process, the K-dimensional Wright-Fisher process, the
Dawson-Watanabe process and the Fleming-Viot process. In all cases, the
number of components involved in the filtering distributions increases
rapidly with the number of observations. Although this could render the
algorithm impractical for long observation sequences and undermine its
practical relevance, the mathematical form of the filtering distributions
suggest that the number of components which contribute most to the mixture
remains small. This suggests several efficient natural approximation
strategies. We assess the performance of these strategies in terms of
accuracy, speed and prediction, benchmarked against the exact solution.
(Joint work with Matteo Ruggiero and Omiros Papaspiliopoulos).

A preprint of this work is available at: https://arxiv.org/abs/2006.03452

[1] O. Papaspiliopoulos and M. Ruggiero, “Optimal filtering and the dual
process,” Bernoulli, vol. 20, no. 4, pp. 1999–2019, 2014.
[2] O. Papaspiliopoulos, M. Ruggiero, and D. Spano, “Conjugacy properties
of time-evolving Dirichlet and gamma random measures,” Electron. J. Stat.,
vol. 10, no. 2, pp. 3452–3489, 2016.

*******************************************************

More details to attend the webinar:

link to attend:
https://unimib.webex.com/unimib/onstage/g.php?MTID=e301e542cc5af6058f9b5599ba8a5930b

Event number (access code): 174 839 4047
Event password: 09122020

*******************************************************

The webinar is part of the series of DEMS Statistics Webinars organized by
the Department of Economics, Management and Statistics (DEMS) of the
University of Milano - Bicocca. More details can be found here:

https://dems.unimib.it/it/argomento-eventi/seminars/dems-seminars
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20201204/fd1eae39/attachment.html>