Zusammenfassung
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.
Nutzer