Skip to yearly menu bar Skip to main content


Learning deep kernels for exponential family densities

Li Kevin Wenliang · D.J. Sutherland · Heiko Strathmann · Arthur Gretton

Pacific Ballroom #221

Keywords: [ Unsupervised Learning ] [ Others ] [ Kernel Methods ]


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.

Live content is unavailable. Log in and register to view live content