BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:1645@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20170320T110000
DTEND;TZID=Europe/Paris:20170320T120000
DTSTAMP:20170305T100000Z
URL:https://www.i2m.univ-amu.fr/evenements/approximate-bayesian-computatio
 n-using-random-forests/
SUMMARY: (...): Approximate Bayesian Computation using Random Forests
DESCRIPTION:: Approximate  Bayesian  Computation  (ABC)  has  grown  into  
 a  standard methodology  to  handle Bayesian inference in models associate
 d with intractable likelihood functions.In a first part\, we will show how
  our ABC Random Forests (RF) methodology can be used to select a model in 
 a Bayesian context. We modify the way Bayesian model selection is both und
 erstood and operated\, in that we rephrase the inferential goal as a class
 ification problem\, first predicting the model that best fits the data wit
 h RF and postponing the approximation of the posterior probability of the 
 selected model for a second stage also relying on RF. Compared with earlie
 r implementations of ABC model choice\, the ABC RF approach offers several
  potential improvements:(i) it often has a larger discriminative power amo
 ng the competing models\, (ii) it is more robust against the number and ch
 oice of statistics summarizing the data\, (iii) the computing effort is dr
 astically reduced (with a gain in computation efficiency of at least 50) a
 nd (iv) it includes an approximation of the posterior probability of the s
 elected model. In a second part\, we will consider parameter estimation qu
 estions. We advocate the derivation of a random forest for each component 
 of the parameter vector\, a tool from which an approximation to the margin
 al posterior distribution can be derived.  Correlations between parameter 
 components are handled by separate random forests. We will show that this 
 technology offers significant gains in terms of robustness to the choice o
 f the summary statistics and of computing time\, when compared with the st
 andard ABC solutions.In the last part\, we will cover some population gene
 tics applications.Paper 1http://bioinformatics.oxfordjournals.org/content/
 32/6/859Paper 2https://arxiv.org/abs/1605.05537http://www.math.univ-montp2
 .fr/~marin/
CATEGORIES:Séminaire,Mathématiques-Évolution-Biologie
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20161030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR