Time: 2015年6月29日 15：00-17：00

Venue: 理科一号楼1114室

Speaker: Xi Chen, Assistant Professor, New York University （联系人：姚远）

Abstract:
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost. In this talk, we investigate the statistical estimation problem in crowdsourcing for categorical labeling task, i.e., how to estimate true labels and workers’ quality from the noisy labels provided by non-expert crowdsourcing workers

The MLE-based Dawid-Skene estimator has been widely used for this problem. However, it is hard to theoretically justify its performance due to the non-convexity of log-likelihood function. We propose a two-stage algorithm where the first stage uses the spectral method to obtain an initial estimate of parameters and the second stage refines the estimation via the EM algorithm. We show that our algorithm achieves the optimal convergence rate up to a logarithmic factor.

(Joint work with Yuchen Zhang, Dengyong Zhou and Michael I. Jordan.)

Bio:
Xi Chen is an Assistant Professor at New York University Stern School of Business. His primary research interests encompass machine learning & optimization, high-dimensional statistics, and operations research. He is developing parametric and non-parametric statistical methods as well as efficient optimization algorithms to address challenges in high-dimensional data analysis. He studies statistical learning and online decision making for crowdsourcing. He also investigates operations research problems, like the optimal network design in process flexibility and personalized revenue management. He was the receipt of Google Faculty Research Award, Simons-Berkeley Research Fellowship and IBM Ph.D. Fellowship.

Before joining NYU Stern, he did a one-year postdoc with Professor Michael Jordan at University of California, Berkeley. He received his M.S. in Industrial Administration and Operations Research from Tepper School of Business, and his Ph.D. in Machine Learning from School of Computer Science all at Carnegie Mellon University.