BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deriving complete constraints in discrete hidden variable DAGs: so
 me practical issues - Erin Gabriel (Københavns Universitet (University of
  Copenhagen))
DTSTART:20260305T144500Z
DTEND:20260305T153000Z
UID:TALK244420@talks.cam.ac.uk
DESCRIPTION:Hidden variable DAGs can sometimes imply constraints on the ob
 servable distribution that are more complex than simple conditional indepe
 ndence relations. Knowing the complete set of observable constraints is id
 eal\, but this can be difficult to determine in many settings. In models w
 ith categorical observed variables we define a class of models where our p
 roposed systematic method for deriving constraints provides the complete s
 et of observable constraints. Although this provides the complete set of o
 bservable constraints\, there are still some practical issues. We have a m
 ethod for reducing the candidate non-trivial constraints\, but determining
  which constraints are actually non-trivial and thus useful can still be t
 he challenge. Additionally\, the method\, although scalable in the number 
 of districts\, does not scale well in the complexity of any given district
 . Finally\, the class of models where the method can be applied is well-de
 fined but\, to our knowledge\, it is not yet known what models outside the
  class have equivalent constraints to ones inside the class. We illustrate
  the method in several new settings\, including ones that imply both inequ
 ality and equality constraints.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR