Constantinos Daskalakis

Constantinos “Costis” Daskalakis is a professor in MIT’s Department of Electrical Engineering and Computer Science and a principal investigator in the Computer Science and Artificial Intelligence Laboratory. He is also a PI with the Institute for Data, Systems, and Society’s Laboratory for Information and Decision Systems and Operations Research Center. Daskalakis works on computation theory and its interface with game theory, economics, probability theory, machine learning and statistics. He has resolved long-standing problems about the computational complexity of the Nash equilibrium, the mathematical structure and computational complexity of multi-item auctions, and the behavior of machine-learning methods. His recent work is focused on statistical hypothesis testing and learning in high-dimensional settings, the structure and concentration properties of high-dimensional distributions, as well as statistical inference from biased, dependent, or strategic data.

Daskalakis has received a Simons Investigator Award, the International Mathematical Union’s Rolf Nevanlinna Prize, an ACM Grace Murray Hopper Award, a Bodossaki Foundation Distinguished Young Scientists Award, and an ACM Doctoral Dissertation Award. He earned a BS in electrical and computer engineering from the National Technical University of Athens, and a PhD in electrical engineering and computer sciences from the University of California, Berkeley.

Publications

• Daskalakis, C., Gouleakis, T., Tzamos, C., Zampetakis, M. (2019). Computationally and Statistically Efficient Truncated Regression. In the 32nd Annual Conference on Learning Theory (COLT).
• Daskalakis, C., Dikkala, N., Panageas, I. (2019). Regression from Dependent Observations. In the 51st Annual ACM Symposium on the Theory of Computing (STOC).
• Daskalakis, C. and Panageas, I. (2019). Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization. In the 10th Innovations in Theoretical Computer Science (ITCS).
• Daskalakis, C. and Panageas, I. (2018). The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization. In the 32nd Annual Conference on Neural Information Processing Systems (NeurIPS).

Media

• May 8, 2019: CSAIL News, CSAIL’s Daskalakis wins ACM Grace Murray Hopper Award.
• August 1, 2018: Quanta Magazine, A poet of computation who uncovers distant truths.
• February 4, 2016: MIT News, Computer science meets economics.
• June 18, 2013: MIT Technology Review, Gaming the system.