BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning non-DAGs by learning DAGs - James Cussens (University of 
 Bristol)
DTSTART:20260306T091500Z
DTEND:20260306T100000Z
UID:TALK244426@talks.cam.ac.uk
DESCRIPTION:Although learning directed graphical (DAG) models (aka "Bayesi
 annetworks") from data is known to be an NP-hard problem\, even with nolat
 ent or selection variables\, it remains substantially easier thanlearning 
 many other model classes (e.g. DAGs with latent and selectionvariables). H
 owever\, if our ultimate goal is data-driven suggestion ofplausible causal
  models then restricting to 'vanilla' DAG models maylead us to miss good c
 ausal models. One option\, explored in this talk\,is to learn a set of van
 illa DAG models which are well supported bythe data\, and look for models 
 from a more general class whichare 'near' to members of this set. Studeny'
 s imset representation ofconditional independence models will be used to f
 rame thisinvestigation. Imset representation does not make difficult probl
 emsof model evaluation and model search go away\, but provides a helpfulun
 iform representation of models.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR