Efficient and principled score estimation with Nyström kernel exponential families

  title={Efficient and principled score estimation with Nystr{\"o}m kernel exponential families},
  author={Dougal J. Sutherland and Heiko Strathmann and Michael Arbel and Arthur Gretton},
We propose a fast method with statistical guarantees for learning an exponential family density model where the natural parameter is in a reproducing kernel Hilbert space, and may be infinite-dimensional. The model is learned by fitting the derivative of the log density, the score, thus avoiding the need to compute a normalization constant. Our approach improves the computational efficiency of an earlier solution by using a low-rank, Nyströmlike solution. The new solution retains the… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 20 times over the past 90 days. VIEW TWEETS
1 Citations
28 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.

Similar Papers

Loading similar papers…