Our asymptotic results show that the resulting procedure performs as well as the oracle estimator, which knows in advance the mean regression function. Hao writes down steps to solving problems and doesn't just assume you should already know things, which is a HUGE plus. One of the major problems in ultrahigh dimensional regression is the high spurious correlation between the unobserved realized noise and some of the predictors. The detection of the change points, namely the positions where the mean changes, is an important problem in such fields as engineering, economics, climatology and bioscience.
Sometimes it can be hard to understand him because of his thick Chinese accent, but he is very accessible if one needs help. Ning’s research is partially supported by National Science Foundation and Simons Foundation. Qing Hao received his B.E. Quiz once every week at first 10 minutes of class, but if you pay attention in lectures you should have no problem answering them. Partial credit is given. I received my B.S. Manuscripts. degree in Thermal Engineering from Tsinghua University, China, in 2001.
We propose a two-stage refitted procedure via a data splitting technique, called refitted cross-validation, to attenuate the influence of irrelevant variables with high spurious correlations.
in Mathematics from Peking University, and Ph.D. from the Department of Mathematics at Stony Brook University. We characterize the theoretical properties of SaRa and show its superiority over other commonly used algorithms. He is a relatively easy grader and wants his students to succeed.Professor Hao is a really great guy and he really knows the material but his heavy accent makes it very hard to understand him. No complex optimization tools are needed, since only OLS-type calculations are involved; the iFOR algorithms avoid storing and manipulating the whole augmented matrix, so the memory and CPU requirement is minimal; the computational complexity is linear in p for sparse models, hence feasible for p ≫ n. Theoretically, we prove that they possess sure screening property for ultra-high dimensional settings. Computationally, the iFOR procedures are designed to be simple and fast to implement.
Hao, N., Niu, Y.S., Xiao, F. and Zhang, H. (2018) A Super Scalable … Scholarly Contributions Journals/Publications.
Sometimes it can be hard to understand him because of his thick Chinese accent, but he is very accessible if one needs help. He then obtained his M.S. Together they form a unique fingerprint. Teaching. degree from the University of Texas at Austin in 2004, and his Ph.D. degree from the Massachusetts Institute of Technology (MIT) in 2010, both in Mechanical Engineering. I am an associate professor of Mathematics at the University of Arizona (UA). The simulation studies lend further support to our theoretical claims. Recent advances in variable selection in ultrahigh dimensional linear regression make this problem accessible. Their performances can be improved by the refitted cross-validation method proposed. In this article, we propose to tackle these issues by forward-selection based procedures called iFOR, which identify interaction effects in a greedy forward fashion while maintaining the natural hierarchical model structure. 2 Similar Profiles However, there is scant literature on the theoretical properties of those algorithms.