talk by David Arbour
Foundations of Data Science Seminar Series
October 29, 2020
3:30 PM - 4:30 PM
Title: General Identification of Dynamic Treatment Regimes Under Interference
Speaker: David Arbour, Adobe Research
Abstract: In many applied fields, researchers are often interested in tailoring treatments to unit-level characteristics in order to optimize an outcome of interest. Methods for identifying and estimating treatment policies are the subject of the dynamic treatment regime literature. Separately, in many settings the assumption that data are independent and identically distributed does not hold due to inter-subject dependence. The phenomenon where a subject's outcome is dependent on his neighbor's exposure is known as interference. These areas intersect in myriad real-world settings. In this paper we consider the problem of identifying optimal treatment policies in the presence of interference. Using a general representation of interference, via Lauritzen-Wermuth-Freydenburg chain graphs (Lauritzen and Richardson, 2002), we formalize a variety of policy interventions under interference and extend existing identification theory (Tian, 2008; Sherman and Shpitser, 2018). Finally, we illustrate the efficacy of policy maximization under interference in a simulation study.
Date posted
Oct 19, 2020
Date updated
Oct 19, 2020
Speakers
David Arbour | Research Scientist | Adobe Research
David Arbour is a research scientist at Adobe research where he primarily works on problems in causal inference and discovery with a particular focus on solutions employing machine learning and settings involving dependent data. Prior to Adobe, David worked in the core data science team at Facebook, and received his PhD in computer science from the University of Massachusetts Amherst.