BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Are our DAGs correct? Recent developments in causal discovery eval
 uation - Jonas Wahl (German Research Centre for Artificial Intelligence)
DTSTART:20260306T111500Z
DTEND:20260306T120000Z
UID:TALK244432@talks.cam.ac.uk
DESCRIPTION:Causal graphical models are considered important tools to inte
 grate expert knowledge into statistical data analysis. As consequence\, pr
 actitioners often face the challenge to evaluate the quality of their hypo
 thesized causal models. This issue becomes particularly salient for causal
  graphical models obtained through a causal discovery method in which case
  most or all of the available data has already been used in the discovery 
 task. In this talk\, we will review recent developments regarding the eval
 uation of causal structure learning methods and the quality of their outpu
 ts. In particular\, we will discuss to which degree assumption violations 
 can be detected in causal discovery and how method testing often introduce
 s additional assumptions that need to be weighted carefully against the as
 sumptions of the initial learning algorithm.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR