BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251107T182336EST-7289X9VMdj@132.216.98.100
DTSTAMP:20251107T232336Z
DESCRIPTION:Bayesian nonparametric inference for discovery probabilities.\n
 \nThe longstanding problem of discovery probabilities dates back to World 
 War II with Alan Turing codebreaking the Axis forces Enigma machine at Ble
 tchley Park. The problem can be simply sketched as follows. An experimente
 r sampling units (say animals) from a population and recording their type 
 (say species) asks: What is the probability that the next sampled animal c
 oincides with a species already observed a given number of times? or that 
 it is a newly discovered species? Applications are not limited to ecology 
 but span bioinformatics\, genetics\, machine learning\, multi- armed bandi
 ts\, and so on. In this talk I describe a Bayesian nonparametric (BNP) app
 roach to the problem and compare it to the original and highly popular est
 imators known as Good-Turing estimators. More specifically\, I start by re
 calling some basics about the Dirichlet process which is the cornerstone o
 f the BNP paradigm. Then I present a closed form expression for the poster
 ior distribution of discovery probabilities which naturally leads to simpl
 e credible intervals. Next I describe asymptotic approximations of the BNP
  estimators for large sample size\, and conclude by illustrating the propo
 sed results through a benchmark genomic dataset of Expressed Sequence Tags
 .\n
DTSTART:20170523T193000Z
DTEND:20170523T203000Z
LOCATION:CA\, QC\, Sherbrooke\, Seminar Statistique Sherbrooke\, 2500 Boul.
  de l'Université
SUMMARY:Julyan Arbel\, INRIA\, Université Grenoble Alpes\, France
URL:/mathstat/channels/event/julyan-arbel-inria-univer
 site-grenoble-alpes-france-268255
END:VEVENT
END:VCALENDAR