Stefanie Jegelka

Stefanie Jegelka is an associate professor in MIT’s Department of Electrical Engineering and Computer Science. She is also an investigator at the Institute for Data, Systems, and Society, the Computer Science and Artificial Intelligence Laboratory and the Operations Research Center. Her research focuses on algorithmic machine learning, and spans modeling, optimization algorithms, theory and applications. In particular, her research group has been working on exploiting mathematical structure for discrete and combinatorial machine learning problems, for robustness and for scaling machine learning algorithms.

Jegelka has received a Sloan Research Fellowship, an NSF Career Award, a DARPA Young Faculty Award, a Google research award and a German Pattern Recognition Award. She earned a PhD at the Max Planck Institutes in Tuebingen and at ETH Zurich, and was a postdoc at University of California, Berkeley.

Selected Publications

• Chuang, C.Y., Mroueh, Y., Greenewald, K., Torralba, A., and Jegelka, S. (2021). Measuring Generalization with Optimal Transport. Conference and Workshop on Neural Information Processing Systems (NeurIPS)
• Gamitry, K., Aliakbarpour, M., and Jegelka, S. (2020). Testing Determinantal Point Processes. Conference and Workshop on Neural Information Processing Systems (NeurIPS)
• Zhang, J., Lin, H., Jegelka, S., Sra, S., and Jadbabaie, A. (2020). Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions. International Conference on Machine Learning (ICML).

Media

• March 20, 2019: MIT News, Women in Data Science conference unites global community of researchers and practitioners.
• June 11, 2018: MITei News, Fabrication of new materials: Designing “recipes” using artificial intelligence.
• December 17, 2017: MIT News, Can computers help us synthesize new materials?
• November 6, 2017: LIDS News, LIDS Affiliate Stefanie Jegelka Awarded NSF BIGDATA Grant.