BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"Asymptotic equivalence between density estimation  and Gaussian w
 hite noise revisited"
DTSTART:20170118T150000
DTEND:20170118T160000
DTSTAMP:20260407T003900Z
UID:1d8d26d3e4a6dd6ba3b4b1a618e55a306b40c6e3da91794bc78aba54
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Kolyan RAY (Leiden University) \nAsymptotic equivalence be
 tween two statistical models means that they have the same asymptotic (lar
 ge sample) properties with respect to all decision problems with bounded l
 oss. In nonparametric (infinite-dimensional) statistical models\, asymptot
 ic equivalence has been found to be useful since it can allow one to deriv
 e certain results by studying simpler models. One of the key results in th
 is area is Nussbaum’s theorem\, which states that nonparametric density 
 estimation is asymptotically equivalent to a Gaussian shift model\, provid
 ed that the densities are smooth enough and uniformly bounded away from ze
 ro.\n \nWe will review the notion of asymptotic equivalence and existing 
 results\, before presenting recent work on the extent to which one can rel
 ax the assumption of being bounded away from zero. We further derive the o
 ptimal (Le Cam) distance between these models\, which quantifies how close
  they are for finite-samples. As an application\, we also consider Poisson
  intensity estimation with low count data. This is joint work with Johanne
 s Schmidt-Hieber.\n \n 
LOCATION:CIB - BI A0 448 http://plan.epfl.ch/?room=BIA0448
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR