Fall 2016
Seminars are held on Thursdays at 4:00PM. Please note the location for each event in the schedule below. For questions about the seminar schedule, please contact Antai Wang.
Date: October 13, 2016
Speaker: Xi Chen
Department of Information, Operations, and Management Sciences,
Stern School of Business at New York University
Title: "Statistical Inference for Model Parameters with Stochastic Gradient Descent"
Abstract:
In this talk, we investigate the problem of statistical inference of the true model parameters based on stochastic gradient descent (SGD). To this end, we propose two consistent estimators of the asymptotic covariance of the average iterate from SGD: (1) an intuitive plug-in estimator and (2) a computationally more efficient batch-means estimator, which only uses the iterates from SGD. As the SGD process forms a time-inhomogeneous Markov chain, our batch-means estimator with carefully chosen increasing batch sizes generalizes the classical batch-means estimator designed for time-homogenous Markov chains. Both proposed estimators allow us to construct asymptotically exact confidence intervals and hypothesis tests. We further discuss an extension to conducting inference based on SGD for high-dimensional linear regression.
Bio:
Xi Chen is an assistant professor at Department of Information, Operations, and Management Sciences at Stern School of Business at New York University. Before that, he was a Postdoc in the group of Prof. Michael Jordan at UC Berkeley. He obtained his Ph.D. from the Machine Learning Department at Carnegie Mellon University (CMU); and his Masters degree in Industry Administration and Operations Research from the Tepper School of Business at CMU.
He studies machine learning, high-dimensional statistics and operations research. He is developing parametric and non-parametric statistical methods as well as optimization algorithms to address challenges in high-dimensional data analysis. He investigates machine learning foundations and sequential analysis for crowdsourcing. He also studies operations research/management problems, such as the optimal network design in process flexibility, and data-driven revenue management. He received Simons-Berkeley Research Fellowship and Google Faculty Research Award.