BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:How close are these distributions? A brief introduction to statist
 ical distances and divergences. - David Burt\, University of Cambridge
DTSTART:20220511T100000Z
DTEND:20220511T113000Z
UID:TALK172094@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:The question of whether two probability distributions are `clo
 se' to each other arises in many contexts in statistics and machine learni
 ng\, including hypothesis testing\, approximate Bayesian inference and gen
 erative modelling. However\, what it means for two probability distributio
 ns to be `close' is somewhat subtle. In this reading group\, we will give 
 an overview of some of the different ways of measuring distance between pr
 obability distributions\, as well as relationships between these notions o
 f distance.  \n\nRequired Reading:\nNone.\n\nReferences and Further (Optio
 nal) Reading:\n\n# On Integral Probability Metrics\, φ-Divergences and\nB
 inary Classification. Bharath K. Sriperumbudur\, Kenji Fukumizu\, Arthur G
 retton\, Bernhard Schölkopf and Gert R.G. Lanckrie. 2009.\n# A Kernel Two
 -Sample Test. Arthur Gretton\, Karsten M. Borgwardt\, Malte J. Rasch\, Ber
 nhard Schölkopf\, Alexander Smola.\n# Lecture Notes on Information Theory
 . Yury Polyanskiy and Yihong Wu. http://www.stat.yale.edu/~yw562/teaching/
 itlectures.pdf. (Particularly chapter 6 and 7 on f-divergences).\n# Optima
 l transport\, old and new. Cedric Villani. Chapter 6.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR