Abstract
The kernel exponential family is a rich class of distributions,which can be
fit efficiently and with statistical guarantees by score matching. Being
required to choose a priori a simple kernel such as the Gaussian, however,
limits its practical applicability. We provide a scheme for learning a kernel
parameterized by a deep network, which can find complex location-dependent
local features of the data geometry. This gives a very rich class of density
models, capable of fitting complex structures on moderate-dimensional problems.
Compared to deep density models fit via maximum likelihood, our approach
provides a complementary set of strengths and tradeoffs: in empirical studies,
the former can yield higher likelihoods, whereas the latter gives better
estimates of the gradient of the log density, the score, which describes the
distribution's shape.
Users
Please
log in to take part in the discussion (add own reviews or comments).