BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Scalable causal discovery for statistically efficient causal infer
 ence - Sara Magliacane (University of Amsterdam)
DTSTART:20260313T140000Z
DTEND:20260313T150000Z
UID:TALK244318@talks.cam.ac.uk
CONTACT:Po-Ling Loh
DESCRIPTION:Causal discovery methods can identify valid adjustment sets fo
 r causal effect estimation for a small set of target variables\, even when
  the underlying causal graph is unknown. Global causal discovery methods f
 ocus on learning the whole causal graph and therefore enable the recovery 
 of optimal adjustment sets\, i.e.\, sets with the lowest asymptotic varian
 ce\, but they quickly become computationally prohibitive as the number of 
 variables grows. Local causal discovery methods offer a more scalable alte
 rnative by focusing on the local neighborhood of the target variables\, bu
 t they are restricted to statistically suboptimal adjustment sets.\n\nIn t
 his talk\, I will present two recent methods that combine the computationa
 l efficiency of local methods with the statistical optimality of global ca
 usal discovery methods. First\, I will describe the Sequential Non-Ancesto
 r Pruning (SNAP) framework (https://arxiv.org/abs/2502.07857). SNAP progre
 ssively identifies and prunes definite non-ancestors of the target variabl
 es during the causal discovery process. We show that the resulting subgrap
 h is sufficient for identifying the causal relations between the targets a
 nd their efficient adjustment sets. Then\, I will introduce Local Optimal 
 Adjustments Discovery (LOAD) (https://arxiv.org/abs/2502.07857)\, a method
  for identifying optimal adjustment sets from local information. As a firs
 t step\, LOAD identifies the causal relation between the targets and tests
  if the causal effect is identifiable by using only local information. If 
 it is identifiable\, it then finds the optimal adjustment set by leveragin
 g local causal discovery to infer the mediators and their parents. Otherwi
 se\, it returns the locally valid parent adjustment sets based on the lear
 ned local structure. For both methods\, I will show that on our evaluation
  they outperform global methods in scalability\, while providing more accu
 rate effect estimation than local methods.
LOCATION:MR12\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR