BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:410@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20240919T140000
DTEND;TZID=Europe/Paris:20240919T140000
DTSTAMP:20260828T120025Z
URL:https://isdm.umontpellier.fr/events/controlling-for-discrete-unmeasure
 d-confounding-in-nonlinear-causal-models-2/
SUMMARY:Controlling for Discrete Unmeasured Confounding in Nonlinear Causal
  Models
DESCRIPTION:Online\n\nMachine Learning in Montpellier\, Theory &amp\; Pract
 ice\n\nUnmeasured confounding is a major challenge for identifying causal 
 relationships from non-experimental data. Here\, we propose a method that 
 can address unmeasured discrete confounding. Extending recent identifiabil
 ity results in deep latent variable models\, we show theoretically that co
 nfounding can be detected and corrected under the assumption that the obse
 rved data is a piecewise affine transformation of a latent Gaussian mixtur
 e model and that the identity of the mixture components is confounded. We 
 provide a flow-based algorithm to estimate this model and perform deconfou
 nding. Experimental results on synthetic and real-world data provide suppo
 rt for the effectiveness of our approach.\n\nMachine Learning in Montpelli
 er\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR