Charles E. Leiserson
Professor, Department of Electrical Engineering and Computer Science; Associate Director, Computer Science and Artificial Intelligence Laboratory
Who they work with
Categories
Charles E. Leiserson is the Edwin Sibley Webster Professor in MIT’s Department of Electrical Engineering and Computer Science, and the former associate director and chief operating officer for the Computer Science and Artificial Intelligence Laboratory. He is faculty director of the MIT-Air Force AI Accelerator. His research centers on the theory and practice of performance engineering, where he develops algorithms and software to make computationally intensive tasks run quickly with minimal computing resources. His current focus is Fast AI. As computer performance due to semiconductor miniaturization dwindles with the end of Moore’s Law, Leiserson sees the opportunity to speed up applications by making software more efficient. His group is currently engaged in a major effort with IBM Research to develop fast, graph-based machine-learning applications for anti-money laundering and other applications.
His research contributions include the Cilk multithreaded programming language and runtime system, the fat-tree interconnection network, systolic architectures, cache-oblivious algorithms, and the Tapir compiler technology. His co-authored textbook, Introduction to Algorithms, has sold over 800,000 copies and is the one of the most cited publications in computer science. He is an elected fellow of the American Association for the Advancement of Science, Association for Computing Machinery, Institute of Electrical and Electronics Engineers, and Society for Industrial and Applied Mathematics and is a member of the National Academy of Engineering. His awards include an ACM-IEEE Computer Society Ken Kennedy Award, an IEEE Computer Society Taylor L. Booth Education Award and an ACM Paris Kanellakis Theory and Practice Award. He earned a BS from Yale University, and a PhD from Carnegie Mellon University.
Selected Publications
- Bellei, C., Xu, M., Phillips, R., Robinson, T., Weber, M., Kaler, T., Leiserson, C. E., Arvind, & Chen, J. (2024). The shape of money laundering: Subgraph representation learning on the blockchain with the Elliptic2 dataset. In Proceedings of the KDD MLF ’24, August 26, 2024, Barcelona, Spain.
- Kaler, T., Schardl, T., Leiserson, C.E., and Chen, J. (2023). Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching. Proceedings of the 6th MLSys Conference.
- Kaler, T., Ouyang, A., Schardl, T., Leiserson, C.E., and Chen, J. (2022). Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining. Proceedings of the 5th MLSys Conference.
Media
- November 29, 2022: MIT News, Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs
- January 30, 2017: MIT News, Optimizing Code.
- February 9, 2016: MIT News, Three from MIT elected to the National Academy of Engineering.