BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Causal Inference for Treatment Effects: A Theory and Associated Le
 arning Algorithms - Mihaela van der Schaar 
DTSTART:20181011T100000Z
DTEND:20181011T110000Z
UID:TALK110002@talks.cam.ac.uk
CONTACT:Adrian Weller
DESCRIPTION:We investigate the problem of estimating the causal effect of 
 a treatment on individual subjects from observational data\; this is a cen
 tral problem in various application domains\, including healthcare\, socia
 l sciences\, and online advertising. We first develop a theoretical founda
 tion of causal inference for individualized treatment effects based on inf
 ormation theory. Next\, we use this theory\, to construct an information-o
 ptimal Bayesian causal inference algorithm.  This algorithm embeds the pot
 ential outcomes in a vector-valued reproducing kernel Hilbert space and us
 es a multi-task Gaussian process prior over that space to infer the indivi
 dualized causal effects. We show that our model significantly outperforms 
 the state-of-the-art causal inference models. The talk will conclude with 
 a discussion of the impact of this work on precision medicine and clinical
  trials. 
LOCATION:Engineering Department\, CBL Room BE-438.
END:VEVENT
END:VCALENDAR