BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261120T133618EST-0543xeAdXs@132.216.98.100
DTSTAMP:20261120T183618Z
DESCRIPTION:A Circular Analogue to the Bernstein Polynomial Densities\, Bay
 esian Nonparametrics and Large Support Asymptotics\n\nThe use of truncated
  Fourier series in circular distribution modelling has been criticized for
  the lack of control it provides. To address this problem\, we suggest a d
 ensity basis of the trigonometric polynomials that is analogous to the Ber
 nstein polynomial densities. We demonstrate key properties that allow the 
 specification of shape constraints and the efficient simulation of the res
 ulting trigonometric densities. For the purpose of density estimation\, we
  consider random polynomial priors built from this basis and show that pos
 terior means compare favourably to other density estimates previously sugg
 ested in the literature. We give a new result on the Kullback-Leibler supp
 ort of sieve priors that ensures posterior consistency in the estimation o
 f discontinuous densities while known results\, valid under regularity ass
 umptions\, complete the asymptotic picture. Joint work with Simon Guillott
 e.\n
DTSTART:20181004T193000Z
DTEND:20181004T203000Z
LOCATION:Room PK-5115 \, CA\, Pavillon President-Kennedy
SUMMARY:Olivier Binette\, UQAM
URL:https://www.mcgill.ca/mathstat/channels/event/olivier-binette-uqam-2902
 03
END:VEVENT
END:VCALENDAR
