Learning for Decision-Making: Dynamics and Economics

Abstract:

Machine learning systems are increasingly used for automated decision making; for example for designing economic policies and for identifying qualified candidates in education or finance. When designing such systems, it is important to consider how changes in the target population or the environment affect the performance of the systems. Moreover, it is important to consider how these systems influence the societal forces that impact the target population. In this talk, I will discuss three lines of my research that take this dynamical and economic perspective on machine learning: learning parameters of auctions in presence of changes in user preferences, learning admission and hiring classifiers that encourage candidates to invest in valuable skill sets, and augmenting human decision making in hiring and admission to increase the diversity of candidates.

Biography

Nika Haghtalab is an Assistant Professor in the Department of Computer Science at Cornell University. Her research is on the theoretical aspects of machine learning and algorithmic economics, with a focus on developing a theory for machine learning that accounts for its interactions with people and organizations. Nika received her Ph.D. from the Computer Science Department of Carnegie Mellon University in 2018. She was a Postdoctoral researcher at Microsoft Research in 2018-2019. Her honors include the CMU School of Computer Science Dissertation award, ACM SIGecom honorable mention dissertation award, Microsoft Research fellowship, Facebook fellowship, IBM fellowship, and Siebel scholarship.