Assistant Professor |
Contact info271 West Hall |
My research is motivated by the challenges of analyzing massive datasets in modern science and engineering. Some topics of recent interest include
adaptive/selective inference,
distributed statistical learning,
robust machine learning.
More broadly, I am interested in the mathematical foundations of data science. I obtained my PhD in 2015 from Stanford University, supervised by Michael Saunders and Jonathan Taylor.
Communication-efficient sparse regression: a one-shot approach, Jason Lee, Qiang Liu, Yuekai Sun, Jonathan Taylor, Journal of Machine Learning Research, to appear.
A geometric approach to large-scale archetypal analysis and non-negative matrix factorization, Anil Damle, Yuekai Sun, Technometrics, to appear.
Exact post-selection inference, with application to the lasso, Jason Lee, Dennis Sun, Yuekai Sun, Jonathan Taylor, Annals of Statistics, vol 44 (2016).
On the model selection consistency of regularized M-estimators, Jason Lee, Yuekai Sun, Jonathan Taylor, Electronic Journal of Statistics, vol 9 (2015).
Proximal Newton-type methods for minimizing composite functions, Jason Lee, Yuekai Sun, Michael Saunders, SIAM Journal on Optimization, vol 24 (2014).
Please see my Google Scholar profile for a list of my publications.
Stats 413: Applied Regression Analysis, Fall 2016.