Title: On the Computational and Statistical Interface and "Big Data"
Speaker: Michael I. Jordan is the Pehong Chen Distinguished Professor in the Department of Electrical Engineering and Computer Science and the Department of Statistics at the University of California, Berkeley.
Abstract: The rapid growth in the size and scope of datasets in science and technology hascreated a need for novel foundational perspectives on data analysis that blendthe statistical and computational sciences. That classical perspectives from thesefields are not adequate to address emerging problems in "Big Data" is apparentfrom their sharply divergent nature at an elementary level---in computerscience, the growth of the number of data points is a source of "complexity"that must be tamed via algorithms or hardware, whereas in statistics, the growthof the number of data points is a source of "simplicity" in that inferences aregenerally stronger and asymptotic results or concentration theorems can be invoked.We present several research vignettes on topics at the computation/statisticsinterface, an interface that we aim to characterize in terms of theoretical tradeoffsbetween statistical risk, amount of data and "externalities" such as computation,communication and privacy. [Joint work with Venkat Chandrasekaran, John Duchi,Martin Wainwright and Yuchen Zhang.]