Abstract:
This will be a tweaked version of my Qualifier talk. I will mostly focus on:
1. The notion of interventional distributions (as defined by Judea Pearl) and how they can be used to identify causal linkages.
2. How directed information can serve as a measure of causality.
3. How conditional directed information can be used to develop an information-theoretic version of Pearl's backdoor criterion for identifying causality from passive observations.
Link to the paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6120270