BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:High-dimensional causal inference - Marloes Maathuis\, ETH Zürich
DTSTART:20131122T160000Z
DTEND:20131122T170000Z
UID:TALK47611@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION:We present recent progress on estimating bounds on causal effe
 cts from observational data\, when assuming that these data are generated 
 from an unknown directed acyclic graph. In particular\, we present the IDA
  algorithm for this purpose. IDA is computationally feasible and consisten
 t for high-dimensional sparse systems with many more variables than observ
 ations. We validated IDA in biological systems\, and will present results 
 on a yeast gene expression data set. Finally\, we discuss possible instabi
 lity issues in high-dimensional settings\, as well as extensions towards a
 llowing for hidden variables and predicting the effect of multiple simulta
 neous interventions.
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR