Speaker: Yazhen Wang (University of Wisconsin-Madison)
Title: Interface of Statistics and Computing in Data Science
Abstract: The role of computation has been central to statistics for decades, and statistics and computing become ever more important in the age of data science. This talk will present the interface of statistics and computing through my statistics work on computational algorithms and computing work on statistics and machine learning. Specifically I will discuss (i) annealing based quantum computing for deep learning; (ii) statistical analysis of gradient descent (accelerated gradient descent and stochastic gradient descent algorithms) in the context of stochastic optimization arising in statistics and machine learning where objective functions are estimated from available data (a training sample or a statistical sample).
Dr. Yazhen Wang is Professor of Statistics at the University of Wisconsin-Madison and served as the department chair from 2015-2018. He obtained his Ph.D in statistics from University of California at Berkeley in 1992. He is the fellows of ASA and IMS. He has served as NSF program director, various committees of ASA, IMS and ICSA; editors of Statistica Sinica and Statistics and Its Interface; associate editors of Annals of Statistics, Annals of Applied Statistics, Journal of the American Statistical Association, Journal of Business & Economic Statistics, Statistica Sinica, and the Econometrics Journal. His research areas include financial econometrics, statistical machine learning, quantum computation, high dimensional statistical inference, nonparametric curve estimation, wavelets and multiscale methods, change points, long-memory processes, and order restricted inference.