Suvrit Sra Image: Misha Sra
Suvrit Sra has joined EECS as an assistant professor and a core faculty member of Institute for Data, Systems, and Society (IDSS).
The appointment took effect in mid-January, said EECS department head Asu Ozdaglar.
Previously, Sra was a principal research scientist in the Laboratory for Information & Decision Systems (LIDS). Before that, he was a senior research scientist at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, and concurrently a visiting faculty member in EECS at University of California Berkeley and in the Machine Learning Department at Carnegie Mellon University. He received his PhD in Computer Science from the University of Texas at Austin.
His research bridges a variety of mathematical topics, including optimization, matrix theory, differential geometry, and probability with machine learning. Recently, he has focused developing algorithmic and complexity foundations of geometric optimization, an emerging subarea of non-convex optimization where geometry (especially non-Euclidean geometry) helps one attain global optimality. More broadly, he is interested in the use of optimization and machine learning for problems materials science, quantum chemistry, synthetic biology, health care, and other fields.
His work has won several awards at machine learning conferences, the 2011 Society for Industrial and Applied Mathematics (SIAM) Outstanding Paper award, and faculty research awards from Criteo and Amazon.
He founded and regularly co-chairs the popular Optimization for Machine Learning (OPT) series of workshops at the annual Conference on Neural Information Processing Systems (NIPS), and edited a well-received book with the same title (MIT Press, 2011).
Sra has been an invited lecturer on optimization at the Machine Learning Summer School (MLSS) and numerous other short schools on machine learning and optimization. He revamped the Berkeley graduate course on Introduction to Convex Optimization, developed a new advanced course on optimization at CMU, and has co-taught graduate and undergraduate machine learning courses in EECS at MIT.