Timezone: »

 
Poster
Multi-view Matrix Factorization for Linear Dynamical System Estimation
Mahdi Karami · Martha White · Dale Schuurmans · Csaba Szepesvari

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #80 #None
in Posters Wed »

We consider maximum likelihood estimation of linear dynamical systems with generalized-linear observation models. Maximum likelihood is typically considered to be hard in this setting since latent states and transition parameters must be inferred jointly. Given that expectation-maximization does not scale and is prone to local minima, moment-matching approaches from the subspace identification literature have become standard, despite known statistical efficiency issues. In this paper, we instead reconsider likelihood maximization and develop an optimization based strategy for recovering the latent states and transition parameters. Key to the approach is a two-view reformulation of maximum likelihood estimation for linear dynamical systems that enables the use of global optimization algorithms for matrix factorization. We show that the proposed estimation strategy outperforms widely-used identification algorithms such as subspace identification methods, both in terms of accuracy and runtime.

Keywords: Time Series Analysis · Unsupervised Learning

Author Information

Mahdi Karami (University of Alberta)
Martha White
Dale Schuurmans (Google)
Csaba Szepesvari (University of Alberta)

More from the Same Authors