Learning to act from observational data
- Uri Shalit - CS-Lecture - Note unusual hour and place
- Tuesday, 3.1.2017, 10:30
- Room 601 Taub Bld.
- Courant Institute of Mathematical Sciences, New York University
The proliferation of data collection in the health, commercial, and economic spheres, brings with it opportunities for extracting new knowledge with concrete policy implications. Examples include individualizing medical practices based on electronic healthcare records, and understanding the implications of job training programs on employment and income. The scientific challenge lies in the fact that standard prediction models such as supervised machine learning are often not enough for decision making from this so-called ''observational data'': Supervised learning does not take into account causality, nor does it account for the feedback loops that arise when predictions are turned into actions. On the other hand, existing causal-inference methods are not adapted to dealing with the rich and complex data now available, and often focus on populations, as opposed to individual-level effects. The problem is most closely related to reinforcement learning and bandit problems in machine learning, but with the important property of having no control over experiments and no direct access to the actor's model. In my talk I will discuss how we apply recent ideas from machine learning to individual-level causal-inference and action. I will introduce a novel generalization bound for estimating individual-level treatment effect, and further show how we use representation learning and deep temporal generative models to create new algorithms geared towards this problem. Finally, I will show experimental results using data from electronic medical records and data from a job training program. Short Bio: ========= Uri Shalit is a postdoctoral researcher in the Courant Institute of Mathematical Sciences, New York University, working at David Sontag's Clinical Machine Learning Lab. His research is focused on creating new methods for finding causal relationships in large-scale high-dimensional observational studies. One of the major motivations for his research is applications in healthcare and clinical medicine. Uri completed his PhD studies at the School of Computer Science & Engineering at The Hebrew University of Jerusalem, under the guidance of Prof. Gal Chechik and Prof. Daphna Weinshall. From 2011 to 2014 Uri was a recipient of Google's European Fellowship in Machine Learning. Previously he has received the Daniel Amit fellowship for significant contribution in theoretical or computational neuroscience, and the Alice and Jack Ormut Foundation PhD Fellowship.