Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Learning deep kernels for exponential family densities
  • Publication Type:
  • Authors:
    Wenliang LK, Sutherland DJ, Strathmann H, Gretton A
  • Publication date:
  • Pagination:
    11693, 11710
  • Published proceedings:
    PMLR 97, 2019
  • Volume:
  • ISBN-13:
  • Status:
  • Name of conference:
    36th International Conference on Machine Learning, ICML 2019
  • Conference place:
    Long Beach, California, USA
  • Conference start date:
  • Conference finish date:
Copyright © 2019 ASME 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.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Gatsby Computational Neurosci Unit
Imaging Neuroscience
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by