After graduating from the Department of Statistics at UC, Berkeley, in May 2010 with a Ph.D. under the supervision of Professor Peter Bickel, I worked at Google as a statistician for one year before I joined the Statistics Department at Carnegie Mellon University as a visiting research scientist.
My main research area is statistical theory and methodology, including:
Analyzing statistical properties of some popular methods and algorithms in machine learning and engineering, such as the particle filter, spectral clustering, and sparse PCA;
Developing new statistical methods that are suitable for high-dimensional, complex data, including dimension reduction, regression, clustering, hypothesis testing, etc;
Understanding the meaning and properties of relevant concepts and methods in related fields from a statistical perspective, such as data privacy, data assimilation, and conformal prediction. These insights will usually lead to useful improvements or modifications.
I am also working on applied problems in astronomy and genetics, using nonparametric smoothing, network estimation, and multiple testing techniques.