The Statistics Seminar speaker for Friday, January 18, 2019, is Po-Ling Loh, an assistant professor in the ECE department at the UW-Madison, with a secondary appointment in the statistics, computer science, and industrial and systems engineering departments. From 2014-2016, Po-Ling was an assistant professor in the statistics department at the Wharton School at the University of Pennsylvania. Po-Ling received an MS in computer science and a PhD in statistics from Berkeley in 2013 and 2014, and a BS in math with a minor in English from Caltech in 2009. She was the recipient of the 2014 Erich L. Lehmann Citation from the Berkeley statistics department for an outstanding PhD dissertation in theoretical statistics, and a best paper award at the NIPS conference in 2012. Po-Ling is a recipient of an NSF CAREER award in statistics.
Talk: Scale calibration for high-dimensional robust regression
Abstract: We present a new method for high-dimensional linear regression when a scale parameter of the error is unknown. The proposed estimator is based on a penalized Huber M-estimator, for which theoretical results on estimation error have recently been proposed in high-dimensional statistics literature. However, variance of the error term in the linear model is intricately connected to the parameter governing the shape of the Huber loss. The main idea is to use an adaptive technique, based on Lepski's method, to overcome the difficulties in solving a joint nonconvex optimization problem with respect to the location and scale parameters.