Identification of causal effects
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Konstantina Palla.
Establishing cause-effect relationships from a combination of data and assumptions is a fundamental part of empirical science.
Graphical models provide a useful framework for representing assumptions about the world and formalizing causal inference.
In this talk, I will first describe a complete algorithm by Tian & Pearl for determining whether a causal effect is identifiable from
observational data for a given graphical model. I will then discuss the relationship between identifiable effects and recursive
factorization of the observational distribution, with potential implications for computationally efficient inference.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|