SPARSE PRIORS ON THE MIXING MATRIX IN INDEPENDENT COMPONENT ANALYSIS
Aapo Hyv#rinen and Raju Karthikesh
In independent component analysis, prior information
on the distributions of the independent components is
often used; some weak information is in fact necessary
for succesful estimation. In contrast, prior informa
tion on the mixing matrix is usually not used. This
is because it is considered that the estimation should
be completely blind as to the form of the mixing ma
trix. Nevertheless, it could be possible to ønd forms
of prior information that are suOEciently general to be
useful in a wide range of applications. In this paper,
we argue that prior information on the sparsity of the
mixing matrix could be a constraint general enough to
merit attention. Moreover, we show that the computa
tional implementation of such sparsifying priors on the
mixing matrix is very simple since in many cases they
can be expressed as conjugate priors. The property of
being conjugate priors means that essentially the same
algorithm can be used as in ordinary ICA.