ISE Welcomes Sam Davanloo Tajbakhsh
Sparse Precision Selection Algorithm for Fitting Gaussian Process Models to Big Data Sets
A seminar by Sam Davanloo Tajbakhsh, Visiting Assistant Professor
Department of Statistics, Virginia Tech
Wednesday, February 10, 2016, 4:00 – 5:00 pm
120 Baker Systems, 1971 Neil Avenue
Fitting Gaussian Process (GP) models via maximum likelihood suffers from nonconvexity of the likelihood function and also from computation complexity for big n problems where n denotes the number of data points. In this talk, we present an algorithm that uses first-order convex optimization algorithms and has provable finite-sample convergence results. The talk includes some applications of GP models for prediction and classification problems in manufacturing, healthcare, and meteorology.
Sam Davanloo Tajbakhsh was born in Tehran, Iran. He received his Ph.D. in Industrial Engineering and Operations Research from the Pennsylvania State University in December 2015 advised by Enrique del Castillo and Necdet Serhat Aybat. Along his Ph.D. studies, he also earned a M.Sc. in Statistics in 2013. He is currently a visiting assistant professor in the department of Statistics affiliated with the Computational Modeling and Data Analytics (CMDA) program. Sam’s research interests include high-dimensional data analysis using convex optimization, and machine learning.