BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Axiomatization of Interventional Probability Distributions - Kayva
 n Sadeghi (University College London)
DTSTART:20241113T150000Z
DTEND:20241113T160000Z
UID:TALK223759@talks.cam.ac.uk
DESCRIPTION:Causal intervention is an essential tool in causal inference. 
 It is axiomatized under the rules of do-calculus in the case of structure 
 causal models.&nbsp\;We provide simple axiomatizations for families of pro
 bability distributions to be different types of interventional distributio
 ns.&nbsp\;Our axiomatizations neatly lead to a simple and clear theory of 
 causality that has several advantages: it does not need to make use of any
  modeling assumptions such as those imposed by structural causal models\; 
 it only relies on interventions on single variables\; it includes most cas
 es with latent variables and causal cycles\; and more importantly\, it doe
 s not assume the existence of an underlying true causal graph--in fact\, a
  &nbsp\;causal graph is a by-product of our theory. We show that\, under o
 ur axiomatizations\, the intervened distributions are Markovian to the def
 ined intervened causal graphs\, and an observed joint probability distribu
 tion is Markovian to the obtained causal graph\; these results are consist
 ent with the case of structural causal models\, and as a result\, the exis
 ting theory of causal inference applies. &nbsp\;We also show that a large 
 class of natural structural causal models satisfy the axioms presented her
 e\, and in other cases\, the causal graphs generated by an interventional 
 family of distributions act more naturally than those associated to struct
 ural causal models.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR