DEPARTMENT OF STATISTICS
Statistics Colloquium
University of Connecticut
Storrs, Connecticut
The Department of Statistics Cordially invites you to a Colloquium
Professor Haiying Wang
Department of Mathematics and Statistics
University of New Hampshire
Leveraging for Logistic Regression with Big Data
ABSTRACT
For Big Data with large sample size n, it is computationally infeasible to obtain the maximum likelihood estimates for unknown parameters, especially when the maximum likelihood estimates does not have a close-form solution. This paper proposes random sub-sampling algorithms to efficiently approximate the maximum likelihood estimates of unknown parameters in a logistic regression model with binary responses, one of the most commonly used models in practice for classification. We theoretically prove the consistency of the algorithms, develop two optimal sub-sampling strategies and evaluate the performance of the proposed methods using synthetic and real data sets.
DATE: Wednesday, October 22, 2014
TIME: 4:00 p.m.
PLACE: Philip E. Austin Building – Room 105
Coffee will be served at 3:30 in room 326
For more information, contact: Tracy Burke at tracy.burke@uconn.edu