Paper Info
Title
Observational-Interventional Priors for Dose-Response Learning.
Abstract
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.
Year
Venue
Field
2016
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016)
Affine transformation,Econometrics,Confounding,Observational study,Nonparametric statistics,Cognitive skill,Artificial intelligence,Gaussian process,Prior probability,Machine learning,Sample size determination,Mathematics
DocType
Volume
ISSN
Conference
29
1049-5258
Citations 
PageRank 
References 
0
0.34
0
Authors
1
Name
Order
Citations
PageRank
Ricardo Bezerra de Andrade e Silva110924.56