|Jose Costa has been selected to receive a 2005 U-M Horace H. Rackham Graduate School Distinguished Dissertation Award for his thesis, "Random Graphs for Structure Discovery in High-Dimensional Data."|
His research demonstrates how computational efficient and scalable graph constructions, such as Minimal Spanning Trees or k-Nearest Neighbor graphs, can be used to encode both statistical and spatial information and address the problems of dimension reduction and structure discovery in high-dimensional data sets. Solving these problems is essential to take full advantage of today's most complex systems, from video surveillance to medical information equipment for example, that generate massive amounts of new types of data and information.
Costa's dissertation advisor at U-M was Prof. Al Hero. Costa is currently a postdoc fellow with the Center for the Mathematics of Information at Caltech. His research focuses on machine learning and nonparametric estimation and detection for high-dimensional data.