New Collaborative Institute Aims to Explore Theoretical Foundations of Data Science

Joining forces with leading Chicago-area research institutions, Northwestern University colaunched the Institute for Data, Econometrics, Algorithms, and Learning (IDEAL).

IDEAL is a multi-discipline (computer science, statistics, economics, electrical engineering, and operations research) and multi-institution (Northwestern University, Toyota Technological Institute at Chicago, and University of Chicago) institute focused on understanding key aspects of data science theory. Supported by the National Science Foundation HDR TRIPODS program, IDEAL aims to develop the foundations of data science by combining perspectives from algorithms, econometrics, and machine learning.

A key component for the institute is the incorporation of econometrics in the academic dialog around data science. “Northwestern has a strong connection between computer science and economics. It’s an incredibly underexplored area and potential opportunity for this institute,” said Jason Hartline, professor of computer science and codirector of IDEAL.  

Another goal of IDEAL is to establish a broad academic research community around the foundations of data science that combines the strengths of Chicago’s leading academic institutions and translates into opportunities within Chicago’s technology sector. 

The institute’s thematically focused “special quarters,” starting spring 2020 through fall 2022, will coordinate graduate coursework between Evanston and Hyde Park campuses.

Through these academic special quarters, workshops, and external visitors, IDEAL aims to foster interdisciplinary, inter-institute collaborative research. The institute will support the study of three broad research themes:

• High dimensional data analysis: To address algorithmic and statistical challenges in dealing with high dimensional data.
• Data science in strategic environments: To address computational and information theoretic challenges in econometric models of strategic behavior.
• Machine learning and optimization: To address foundational questions in both continuous and discrete optimization and its use in machine learning.

“IDEAL is very timely,” said Aravindan Vijayaraghavan, assistant professor of computer science andcodirector of IDEAL. “You see data science used in every walk of life, but there are so many fundamental data science questions that we don’t understand. There is a lot theory can contribute, and we hope these collaborations will spark new areas of research.”

IDEAL is led by 14 coprincipal investigators from the three participating institutions. From Northwestern University, co-PIs include: Eric Auerbach, Randall Berry, Ivan Canay, Dongning Guo, Jason Hartline, Joel Horowitz, Samir Khuller, Konstantin Makarychev, Aravindan Vijayaraghavan, and Zhaoran Wang. 

IDEAL’s first special quarter, “Inference and Data Science on Networks,” starts March 25, 2020. Learn more about special quarters, events, and participation in IDEAL.