Statistics – Machine Learning
Scientific paper
2011-05-12
L\"ucke, J. and Sheikh, A.-S. Proc. LVA/ICA, LNCS pp. 213-221, 2012
Statistics
Machine Learning
joint first authorship
Scientific paper
We define and discuss the first sparse coding algorithm based on closed-form EM updates and continuous latent variables. The underlying generative model consists of a standard `spike-and-slab' prior and a Gaussian noise model. Closed-form solutions for E- and M-step equations are derived by generalizing probabilistic PCA. The resulting EM algorithm can take all modes of a potentially multi-modal posterior into account. The computational cost of the algorithm scales exponentially with the number of hidden dimensions. However, with current computational resources, it is still possible to efficiently learn model parameters for medium-scale problems. Thus the model can be applied to the typical range of source separation tasks. In numerical experiments on artificial data we verify likelihood maximization and show that the derived algorithm recovers the sparse directions of standard sparse coding distributions. On source separation benchmarks comprised of realistic data we show that the algorithm is competitive with other recent methods.
Lücke Jörg
Sheikh Abdul-Saboor
No associations
LandOfFree
Closed-form EM for Sparse Coding and its Application to Source Separation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Closed-form EM for Sparse Coding and its Application to Source Separation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Closed-form EM for Sparse Coding and its Application to Source Separation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-497215