Timezone: »

 
Poster
Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages
Yin Cheng Ng · Pawel M Chilinski · Ricardo Silva

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #146
in Monday Posters »

Factorial Hidden Markov Models (FHMMs) are powerful models for sequential data but they do not scale well with long sequences. We propose a scalable inference and learning algorithm for FHMMs that draws on ideas from the stochastic variational inference, neural network and copula literatures. Unlike existing approaches, the proposed algorithm requires no message passing procedure among latent variables and can be distributed to a network of computers to speed up learning. Our experiments corroborate that the proposed algorithm does not introduce further approximation bias compared to the proven structured mean-field algorithm, and achieves better performance with long sequences and large FHMMs.

Keywords: Online Learning · (Other) Probabilistic Models and Methods · Variational Inference · Graphical Models · Time Series Analysis
[ PDF] 

Author Information

Yin Cheng Ng (University College London)
Pawel M Chilinski (University College London)
Ricardo Silva (University College London)

More from the Same Authors