Biography (CV)


I am currently an Assistant Professor of Information, Operations and Management Sciences at Stern School of Business at New York University.

Before joining NYU Stern, I did a postdoc with Professor Michael I. Jordan at the University of California, Berkeley. I earned my doctoral degree from the Machine Learning Department at the School of Computer Science at Carnegie Mellon University. My doctoral dissertation, entitled Learning with Sparsity: Structures, Optimization and Applications, was directed by the committee members: Dr. Jaime Carbonell, Dr. Tom Mitchell, Dr. Larry Wasserman, and Dr. Robert Tibshirani (from Stanford). During my Ph.D., I did internships at Microsoft Research Redmond, IBM T.J. Watson Research Center and NEC Lab America.

Before that, I obtained my master of science in Industry Administration (Operations Research) from the ACO (algorithms, combinatorics and optimization) program in the Tepper School of Business at Carnegie Mellon. My master's work is advised by Prof. Manuel Blum.

I was featured in Forbes 30 under 30 in Science and received the Adobe Data Science Research Award, Google Faculty Research Award, Simons-Berkeley Research Fellowship, and IBM Ph.D. Fellowship.

Please note:

  • Unfortunately, I am unable to respond to most inquiries regarding openings for Ph.D. positions in my group (unless you have a strong research record with top publications in machine learning conferences or statistics journals, I might provide you some suggestions for applications). In general, admissions to NYU Stern are handled at a group level committee, not by me.
  • I do not have any research assistant opening nor summer visiting position for undergraduate or master students.
  • Short-term potential visitors (Ph.D. students or faculty) are welcome to contact me. But I usually do not have long-term (e.g., a semeseter or longer) visiting position for outside Ph.D. students.

Research Interests

  • Statistical Inference for Big Data: Inference for Online Data (using Stochastic Gradient Descent), Distributed Data, and High-dimensional Data.
  • Nonparametric Estimation and Shape-restricted Estimation
  • Sequential Analysis and Multi-armed Bandit Learning with Applications to Rank Aggregation, Crowdsourcing, and Revenue Management.
  • Optimization: Non-convex Optimization, Online Stochastic Optimization, and Robust Optimization for Deep Learning
  • Discrete Optimization with Applications to Optimal Network Design in Process Flexibility
  • Please see my publications or Google Scholar profile for more details

(c) 2017 Xi Chen. Design by FCT