BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Statistical implications of group invariance of distributions
DTSTART:20230505T151500
DTEND:20230505T170000
DTSTAMP:20260428T004820Z
UID:09bf2be576b0d95305b1b1cf42bdde2adb50667600f5b6d4518f698f
CATEGORIES:Conferences - Seminars
DESCRIPTION:Peter Orbanz\, UCL\nConsider a large random structure -- a ran
 dom graph\, a stochastic process on the line\, a random field on the grid 
 -- and a function that depends only on a small part of the structure. Now 
 use a family of transformations to ‘move’ the domain of the function o
 ver the structure\, collect each function value\, and average. Under suita
 ble conditions\, the law of large numbers generalizes to such averages\; t
 hat is one of the deep insights of modern ergodic theory.\nThe work I will
  present here shows that central limit theorems and other higher-order pro
 perties also hold. Loosely speaking\, if the i.i.d. assumption of classica
 l statistics is substituted by suitable properties formulated in terms of 
 groups\, the fundamental theorems of inference still hold.\n 
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR