The mathematics of data
Computer Engineering Department, Floor 1, Class 102
Wednesday, 30 December 2015
10:30 - 11:30
Modern data sets are noisy and unstructured and often contain corrupted or incomplete information. At the confluence of optimization, statistics, and computer science a new discipline is emerging to address these challenges. In this talk, I will give an introduction to this area. A special focus will on novel methods and mathematical tools that allow us to glean useful information from seemingly incomplete data sets.
Mahdi Soltanolkotabi obtained his B.S. in electrical engineering at Sharif University of Technology, Tehran, Iran in 2009. He completed his M.S. and Ph.D. in electrical engineering at Stanford University in 2011 and 2014, respectively, under the supervision of Emmanuel Candes. He was a postdoctoral researcher in the Algorithms, People and Machines (AMP) lab at the Department of Electrical Engineering and Computer Science at the University of California, Berkeley from August 2014 – August 2015. He joined the EE Department at USC in 2015 as an assistant professor. His research interests include optimization, machine learning, signal processing, high-dimensional statistics, and geometry with emphasis on applications in information and physical sciences.