Dear Colleagues,
The Division of Biostatistics at the Department of Preventive Medicine invites you to attend the following seminar by our speaker, Dr. Saunak Sen, Preventive Medicine, UTHSC.
Date: Monday, 02/12/2018
Time: 2 P.M.
Place: 4th Floor Conference Room 400 in the Doctors Office Building at 66 N. Pauline Street, Memphis, TN 38105. Please park in the multi-story parking garage adjacent to the Doctors Office Building, and bring your parking card with you so we can give you a validation ticket.
Presenter: Dr. Saunak Sen, Professor, Preventive Medicine, UTHSC
Title: Three algorithms for statistical computing: the MM, EM, and proximal gradient algorithms
Abstract: Many problems in statistical estimation and machine learning boil down to optimization of a criterion such as the log likelihood, the residual sum of squares, or a penalized version. Commonly used algorithms include iteratively reweighted least squares (IWLS) and Newton-Raphson methods. If the objective function depends on a large number of parameters, is not smooth, or is difficult to compute, other methods are needed. In statistics the EM algorithm is a common choice; in machine learning proximal gradient algorithms are useful. It turns out that both are special cases of the MM (minorization-maximization) algorithm. This method is guaranteed to improve the objective function in each iteration under general conditions. We will provide an overview of the three algorithms, and examine their use in penalized regression models.
We look forward to seeing you all among us.
Mehmet Kocak, Ph.D.
Associate Professor of Biostatistics
Department of Preventive Medicine, UTHSC