Title :
Bayesian Generalized Linear Models in a Terabyte World
Author_Institution :
Microsoft Res. Cambridge, Cambridge
Abstract :
This paper introduces extremely fast approximate inference schemes for Bayesian treatments of dynamic generalized linear models. The approximations are tailored variants of quadrature EP. The first forward pass of this fixed point iteration algorithm can be interpreted as a one-step unscented Kalman filter. For on-line applications this filter can handle tens of thousands of updates a second on a current day desktop machine.
Keywords :
Bayes methods; inference mechanisms; regression analysis; Bayesian generalized linear models; Bayesian treatments; approximate inference schemes; desktop machine; fixed point iteration algorithm; one-step unscented Kalman filter; Bayesian methods; Filters; Gaussian distribution; Inference algorithms; Kernel; Large-scale systems; Linear regression; Sampling methods; Statistics; Vectors;
Conference_Titel :
Image and Signal Processing and Analysis, 2007. ISPA 2007. 5th International Symposium on
Conference_Location :
Istanbul
Print_ISBN :
978-953-184-116-0
DOI :
10.1109/ISPA.2007.4383733
