On Identification via EM with Latent Disturbances and Lagrangian Relaxation
2015 (English)Conference paper (Refereed)
In the application of the Expectation Maximization (EM) algorithm to identification of dynamical systems, latent variables are typically taken as system states, for simplicity. In this work, we propose a different choice of latent variables, namely, system disturbances. Such a formulation is shown, under certain circumstances, to improve the fidelity of bounds on the likelihood, and circumvent difficulties related to intractable model transition densities. To access these benefits, we propose a Lagrangian relaxation of the challenging optimization problem that arises when formulating over latent disturbances, and fully develop the method for linear models.
Place, publisher, year, edition, pages
2015. Vol. 48, no 28, 69-74 p.
System identification, expectation maximization, convex relaxation
IdentifiersURN: urn:nbn:se:uu:diva-306933DOI: 10.1016/j.ifacol.2015.12.102OAI: oai:DiVA.org:uu-306933DiVA: diva2:1044750
17th IFAC Symposium on System Identification SYSID 2015 – Beijing, China, 19–21 October 2015
FunderSwedish Research Council, 621-2013-5524