[Ml-stat-talks] FW: Reminder: IDeAS Seminar 3/26/14 @ 3:00 pm

Amit Singer amits at math.Princeton.EDU
Tue Mar 25 18:10:54 EDT 2014

For those who are interested in earth mover distances:


From: Valerie Marino [mailto:vmarino at math.princeton.edu] 
Sent: Tuesday, March 25, 2014 3:49 PM
To: undisclosed-recipients:
Subject: Reminder: IDeAS Seminar 3/26/14 @ 3:00 pm


DATE: Wednesday  March 26 , 2014


PLACE: 110 Fine Hall 

TIME: 3:00 pm 

SPEAKER:William Leeb - Yale University

TITLE: Earth Mover's Distance and Equivalent Metrics

Earth Mover's Distance (EMD) is a robust and interpretable metric for
comparing probability distributions. Unlike conventional distances, EMD
exploits the geometry of the space on which the distributions are defined.
However, it is not easy to compute directly. In this talk, I will present
metrics equivalent to EMD that can be computed fast. I will explain how
these metrics emerge from the theory of Hölder spaces and their duals. I
will also show that in any space equipped with a diffusion semigroup of the
kind widely used in machine learning, there is a natural metric with respect
to which the classical characterizations of Hölder spaces and their duals
generalize. If time permits, I will discuss an analogous theory on spaces
equipped with hierarchical partition trees.


Valerie Marino
Program Secretary
Program in Applied & Computational Mathematics
Tel: 609-258-3703
Fax: 609-258-1735
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20140325/b7fdf0a0/attachment.htm>

More information about the Ml-stat-talks mailing list