University of Cambridge > Talks.cam > Machine Learning @ CUED > Efficient Sampling with Kernel Herding

Efficient Sampling with Kernel Herding

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

The herding algorithm was proposed as a deterministic dynamic system that integrates learning and inference for discrete Markov Random Fields. In this talk, we take a dual view of herding and extend it to continuous spaces by using the kernel trick. The resulting “kernel herding” is an infinite memory deterministic algorithm that approximates a PDF with a collection of samples. We show that kernel herding decreases the error of expectations of functions in the Hilbert space much faster than the usual iid random samples. If time permits, I’ll also talk about the recent development and applications of the herding algorithm.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity