SCS Doctoral Dissertation Award Lecture

Thursday, April 25, 2019 - 4:30pm


Rashid Auditorium 4401 Gates Hillman Centers


NIKA HAGHTALAB, Postdoctoral Researcher, Microsoft Research, New England

Machine learning by the people, for the people

Typical analysis of learning algorithms considers their outcome in isolation from the effects that they may have on the process that generates the data or the entity that is interested in learning. However, current technological trends mean that people and organizations increasingly interact with learning systems, making it necessary to consider these effects, which fundamentally change the nature of learning and the challenges involved. In this talk, I will explore three lines of research from my work on the theoretical aspects of machine learning and algorithmic economics that account for these interactions: learning optimal policies in game-theoretic settings, without an accurate behavioral model, by interacting with people; managing people's expertise and resources in data-collection and machine learning; and addressing belief polarization in learners.

Nika Haghtalab is a postdoctoral researcher at Microsoft Research, New England. In summer 2019, she will join the Department of Computer Science at Cornell University as an Assistant Professor.  Her research is on the theoretical aspects of machine learning and algorithmic economics. She is especially interested in developing a theory for machine learning that accounts for its interactions with people and organizations, and the wide variety of social and economic limitations, aspiration, and behavior they demonstrate.

She recently received the Ph.D. degree from the Computer Science Department of Carnegie Mellon University, where she was co-advised by Avrim Blum and Ariel Procaccia.  Her honors include the CMU School of Computer Science Dissertation award (2018), a Microsoft Research fellowship, a Facebook fellowship, an IBM fellowship, and a Siebel scholarship.

Event Website:

For More Information, Contact:


Distinguished Lecture