Statistics Seminar: Qing Mai

Speaker: Qing Mai

Title: A Doubly-Enhanced EM Algorithm for Model-Based Tensor Clustering

Abstract: Modern scientific studies often collect data sets in the form of tensors. These datasets call for innovative statistical analysis methods. In particular, there is a pressing need for tensor clustering methods to understand the heterogeneity in the data. We propose a tensor normal mixture model approach to enable probabilistic interpretation and computational tractability. Our statistical model leverages the tensor covariance structure to reduce the number of parameters for parsimonious modeling, and at the same time explicitly exploits the correlations for better variable selection and clustering. We propose a doubly-enhanced expectation-maximization (DEEM) algorithm to perform clustering under this model. Both the Expectation-step and the Maximization-step are carefully tailored for tensor data in order to maximize statistical accuracy and minimize computational costs in high dimensions. Theoretical studies confirm that DEEM achieves consistent clustering even when the dimension of each mode of the tensors grows at an exponential rate of the sample size. Numerical studies demonstrate favorable performance of DEEM in comparison to existing methods.

Bio: Qing Mai is Associate Professor, Department of Statistics, at Florida State University. She received her PhD degree in Statistics from University of Minnesota in 2013. Her research interests include classification, clustering analysis, high-dimensional statistics and inference, tensor data analysis, and machine learning. She is passionate about developing novel statistical analysis methods to answer to new challenges as researchers collect increasingly large and complex datasets. She is also devoted to developing efficient algorithms and rigorous theories to accompany the new methods. Her research is partially supported by National Science Foundation. She is currently serving as Associate Editor of Biometrics.

All School of Statistics Seminars are open to the public. A virtual social will take place from 11:30-12:00, following this seminar. To join, visit z.umn.edu/STATSeminarSocial
NOTE: You will need to use a Chrome or Firefox browser to access this virtual platform. The link may not open if you sign in using a mobile device or tablet. The virtual space will not open until approximately 11:30.