Yale researcher Amin Karbasi has received a Young Investigator Award from the Air Force Office of Scientific Research to pursue his project Information Content of Big Data.

The Young Investigator Research Program awarded approximately $19.1 million in grants to 43 scientists and engineers from 37 research institutions and small businesses. The awards are made through a competitive process and recognize scientists “who show exceptional ability and promise for conducting basic research”. This year, AFOSR received over 285 proposals in response to the AFOSR YIP broad agency announcement solicitation, BAA-AFRL-2017-0002.

Karbasi, who is a faculty member at the Yale Institute for Network Science (YINS), submitted an independent proposal that was selected for its potential for creative basic research and to enhance the early career development of an outstanding young investigator.

Professor Karbasi’s project seeks fundamental information limits of learning from big data. In fact, he targets various discrete and continuous optimization methods that rely on sampling from data. He aims to describe a unifying strategy on how such sampling should be done in order to not lose information but gain in terms of computation. He also seeks methods that can use data as a resource to accelerate their procedures. Even though this seems counter intuitive, his recent research shows that intelligent sampling is an effective way to achieve a tradeoff between data and computation. 

An Assistant Professor of Electrical Engineering and Computer Science, Karbasi joined YINS from EPFL, Switzerland (after a year of post-doc at ETHZ) in September 2014. His research lies at the intersection of learning theory, large-scale networks, and optimum information processing.