Timezone: »

 
Poster
Observational-Interventional Priors for Dose-Response Learning
Ricardo Silva

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #14
in Tuesday Posters »

Controlled interventions provide the most direct source of information for learning causal effects. In particular, a dose-response curve can be learned by varying the treatment level and observing the corresponding outcomes. However, interventions can be expensive and time-consuming. Observational data, where the treatment is not controlled by a known mechanism, is sometimes available. Under some strong assumptions, observational data allows for the estimation of dose-response curves. Estimating such curves nonparametrically is hard: sample sizes for controlled interventions may be small, while in the observational case a large number of measured confounders may need to be marginalized. In this paper, we introduce a hierarchical Gaussian process prior that constructs a distribution over the dose-response curve by learning from observational data, and reshapes the distribution with a nonparametric affine transform learned from controlled interventions. This function composition from different sources is shown to speed-up learning, which we demonstrate with a thorough sensitivity analysis and an application to modeling the effect of therapy on cognitive skills of premature infants.

Keywords: (Other) Probabilistic Models and Methods · Graphical Models · Gaussian Processes · Causality
[ PDF] 

Author Information

Ricardo Silva (University College London)

More from the Same Authors