BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//compute-paris-2026//speaker//XB3RCW
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251126T000000
TZNAME:CET
TZOFFSETFROM:+0100
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T030000
RDATE:20271031T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Stop brute-forcing your posteriors: structured Bayesian inference 
 in Julia - Tim Weiland
DTSTART;TZID=Europe/Paris:20261126T100500
DTEND;TZID=Europe/Paris:20261126T103500
DTSTAMP:20260930T112545Z
UID:pretalx-compute-paris-2026-J8TETR@pretalx.com
DESCRIPTION:Mapping disease risk across a region\, modelling how insurance
  claims accumulate\, tracking a fish stock as it rises and falls: these co
 me from different fields\, but the underlying models are alike.\nEach desc
 ribes a smooth\, structured process that we never see directly\, only thro
 ugh noisy data.\nThe standard approach is to hand these models to a genera
 l-purpose sampler and wait.\nThe trouble is that the sampler sees a black 
 box\, and brute-forces structure that the model states plainly.\nBy contra
 st\, a family of specialized methods uses this structure\, and they turn o
 ut to form one spectrum\, from fast (orders of magnitude faster than MCMC)
  to faithful.\nThis talk introduces Latte.jl\, a probabilistic programming
  language for latent Gaussian models that unifies this spectrum of structu
 re-exploiting inference methods.
LOCATION:Room 106
URL:https://pretalx.com/compute-paris-2026/talk/J8TETR/
END:VEVENT
END:VCALENDAR