Upcoming Talks

Ist logo

Approximate Kernel Embeddings of Distributions

Date: Thursday, June 14, 2018 13:00 - 15:00
Speaker: Dino Sejdinovic (Oxford University)
Location: Mondi Seminar Room 2, Central Building
Series: CS Talk Series
Host: Christoph Lampert

Abstract:

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting probability metric, are useful tools for fully nonparametric hypothesis testing and for learning on distributional inputs, i.e. where labels are only observed at an aggregate level. I will give an overview of this framework and describe the use of large-scale approximations to kernel embeddings in the context of Bayesian approaches to learning on distributions and in the context of distributional covariate shift, e.g. where measurement noise on the training inputs may differ from that on the testing inputs
Qr image
Download ICS Download invitation
Back to eventlist