Tuesday, February 26, 2019 - 4:00pm to 5:00pm
Event Calendar Category
LIDS Seminar Series
University of Southern California
Building and Room Number
This talk introduces "Coded Computing”, a new framework that brings concepts and tools from information theory and coding into distributed computing to mitigate several performance bottlenecks that arise in large-scale distributed computing and machine learning, such as resiliency to stragglers and bandwidth bottleneck. Furthermore, coded computing can enable (information-theoretically) secure and private learning over untrusted workers that is gaining increasing importance in various application domains. In particular, we present CodedPrivateML for distributed learning, which keeps both the data and the model private while allowing efficient parallelization of training across untrusted distributed workers. We demonstrate that CodedPrivateML can provide an order of magnitude speedup (up to ~30x) over the cryptographic approaches that rely on secure multiparty computing.
Salman Avestimehr is a Professor of Electrical Engineering and co-director of Communication Sciences Institute at the University of Southern California. He received his Ph.D. in 2008 and M.S. degree in 2005 in Electrical Engineering and Computer Science, both from the University of California, Berkeley. Prior to that, he obtained his B.S. in Electrical Engineering from Sharif University of Technology in 2003. His research interests include information theory and coding, distributed computing, and machine learning. Dr. Avestimehr has received a number of awards, including a Communications Society and Information Theory Society Joint Paper Award, the Presidential Early Career Award for Scientists and Engineers (PECASE), a Young Investigator Program (YIP) award from the U. S. Air Force Office of Scientific Research, a National Science Foundation CAREER award, and several best paper awards. He is currently an Associate Editor for the IEEE Transactions on Information Theory and a General Co-Chair of the 2020 International Symposium on Information Theory (ISIT).