UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning deep kernels for exponential family densities

Wenliang, LK; Sutherland, DJ; Strathmann, H; Gretton, A; (2019) Learning deep kernels for exponential family densities. In: Proceedings of the 36th International Conference on Machine Learning. (pp. pp. 11693-11710). Proceedings of Machine Learning Research (PMLR): Long Beach, CA, USA. Green open access

[thumbnail of wenliang19a.pdf]
Preview
Text
wenliang19a.pdf - Published version

Download (2MB) | Preview

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 features of the local 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, deep maximum-likelihood models can yield higher likelihoods, while our approach gives better estimates of the gradient of the log density, the score, which describes the distribution's shape.

Type: Proceedings paper
Title: Learning deep kernels for exponential family densities
Event: 36th International Conference on Machine Learning (ICML 2019)
Open access status: An open access version is available from UCL Discovery
Publisher version: http://proceedings.mlr.press/v97/wenliang19a.html
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
URI: https://discovery.ucl.ac.uk/id/eprint/10091929
Downloads since deposit
55Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item