Han Liu's Homepage at Princeton University

Han Liu | Email: hanliu@cs.cmu.edu

Gates Hillman Complex 8008, Carnegie Mellon University , 5000 Forbes Ave. Pittsburgh, PA 15213 , Phone: 412. 268. 8699

Biography

Publications

Honors

Teaching

Contact

Research

Modern data acquisition routinely produces massive amounts of very large-scale, ultrahigh-dimensional and highly complex datasets. Driven by the complexity of these datasets, highly adaptive and scalable data analysis procedures are crucially needed. My research lies at the interaction of Modern Statistics and Computer Science. Especially, I am interested in large-scale nonparametric methods, which directly conduct inference in infinite-dimensional spaces and are more flexible to capture the subtleties in modern applications. My long-term goal is to develop a new generation of more powerful and principled statistical theories and machine learning algorithms to explore, understand, and predict large-scale, complex datasets. My current projects include:

(P1) Go-CART: Graph-valued Regression (with Xi Chen, John Lafferty, and Larry Wasserman);
(P2) StARS: Stability Approach to Regularization Selection for High Dimensional Graphical Models (with Kathryn Roeder and Larry Wasserman);
(P3) Forest Density Estimation (with Min Xu, Haijie Gu, Anupam Dasgupta, John Lafferty, and Larry Wasserman);

Useful tools involved in my research include asymptotic statistics, empirical process theory, concentration of measure inequalities, functional and convex analysis, optimization and numerical methods, sub-differential calculus and computational complexity theory, etc.

News: Starting from November 2010, I will become an Assistant Professor in Biostatistics and Computer Science at the Johns Hopkins University. I am now actively looking for future collaborators. Anyone (especially graduate students) are very welcome to drop me a line to discuss possible opportunities.

Biography

In 2010, I received my Joint PhD degrees in Machine Learning and Statistics from the Machine Learning Department within the School of Computer Science at Carnegie Mellon University. My dissertation advisors are John Lafferty and Larry Wasserman. I obtained my M.S. degree in Statistics at Carnegie Mellon University in 2007 and another M.S. in Computer Science at University of Toronto in 2005. Starting from November 2010, I will be an Assistant Professor in Biostatistics and Computer Science at the Johns Hopkins University.

My industrial experience includes summer internships at Microsoft research Redmond, Microsoft Live Search, and Google Research from 2008 to 2010. In 2005, I also worked as a programmer in the automated learning group (ALG) at the National Center for Supercomputing and Applications (NCSA), Champaign, IL.

Publications

Stability Approach to Regularization Selection (StARS) for High Dimensional Graphical Models
Han Liu, Kathryn Roeder and Larry Wasserman
In Advances in Neural Information Processing Systems (NIPS), 23, 2010.
PDF
Graph-Valued Regression
Han Liu, Xi Chen, John Lafferty, and Larry Wasserman
In Advances in Neural Information Processing Systems (NIPS), 23, 2010.
PDF
Multivariate Dyadic Regression Trees for Sparse Learning Problems
Han Liu and Xi Chen
In Advances in Neural Information Processing Systems (NIPS), 23, 2010.
PDF (One of four winning papers in the 2010 ASA Student Paper Competition sponsored by the Statistical Computing Section)
Forest Density Estimation
Han Liu, Min Xu, Haijie Gu, Anupam Dasgupta, John Lafferty, and Larry Wasserman
arXiv:1001.1557, 2010. A conference version has appeared in the 23rd Annual Conference on Learning Theory (COLT), 2010.
PDF
The Group Dantzig Selector
Han Liu, Jian Zhang, Xiaoye Jiang, and Jun Liu
In Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS), (JMLR-WCP)9:461-468, 2010
PDF
Mining Past Query Trails to Label Long and Rare Search Engine Queries
Peter Bailey, Ryen W. White, Han Liu, and Giridhar Kumaran
ACM Transactions on the Web (ACM TWEB) 1(2) 1-25, 2010.
PDF
Learning Spatial-Temporal Varying Graphs with Applications to Climate Data Analysis
Xi Chen, Yan Liu, Han Liu and Jaime G. Carbonell
Proceedings of the Twenty-Fourth Conference on Artificial Intelligence (AAAI), 2010.
PDF
The Nonparanormal: Semiparametric Estimation of High Dimensional Undirected Graphs
Han Liu, John Lafferty, and Larry Wasserman
Journal of Machine Learning Research (JMLR), (10) 2295-2328, 2009.
PDF
Nonparametric Greedy Algorithm for the Sparse Learning Problems
Han Liu and Xi Chen
In Advances in Neural Information Processing Systems (NIPS), 22, 2009.
PDF
On the Estimation and Variable Selection Consistency of the Sum of q-norm Regularized Regression
Han Liu and Jian Zhang
Technical Report, Department of Statistics, Carnegie Mellon University (CMU-STAT-TR-86), 2009.
PDF
Some Two-step Procedures for Variable Selection in High-dimensional Linear Regression
Jian Zhang, Jessie Jeng, and Han Liu
Technical Report, Department of Statistics, Purdue University (Purdue-STAT-TR-08-05), 2009.
PDF
Blockwise Coordinate Descent Procedures for the Multi-task Lasso, with Applications to Neural Semantic Basis Discovery
Han Liu, Mark Palatucci, and Jian Zhang
The Twenty-sixth International Conference on Machine Learning (ICML), 2009.
PDF (Winner of the Best Student Paper Award and Best Overall Paper Honorable Mention)
Sparse Additive Models
Pradeep Ravikumar, John Lafferty, Han Liu, Larry Wasserman
Journal of the Royal Statistical Society: Series B (Statistical Methodology) (JRSSB), 2009.
PDF
On the Estimation Consistency of the Group Lasso and its Applications
Han Liu and Jian Zhang
In Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), (JMLR-WCP)5:376-383, 2009
PDF (Best Paper Award Nominee)
Nonparametric Regression and Classification with Joint Sparsity Constraints
Han Liu, John Lafferty, and Larry Wasserman
In Advances in Neural Information Processing Systems (NIPS), 21, 2008.
PDF
Discovering a Semantic Basis of Neural Activity using Simultaneous Sparse Approximation
Mark Palatucci, Tom Mitchell, and Han Liu
In Sparse Optimization and Variable Selection Workshop (ICML), 2008.
PDF
SpAM: Sparse Additive Models
Pradeep Ravikumar, Han Liu, John Lafferty and Larry Wasserman
In Advances in Neural Information Processing Systems (NIPS), 20, 2007.
PDF
Sparse Nonparametric Density Estimation in High Dimensions using the Rodeo
Han Liu, John Lafferty, and Larry Wasserman
Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS),JMLR-WCP vol 2:283-290, 2007.
PDF
Towards the Prediction of Protein Abundance from Tandem Mass Spectrometry Data
Anthony Bonner and Han Liu
Sixth SIAM International Conference on Data Mining (SDM), 2006.
PDF
A Framework for Efficient Association Rule Mining in XML Data
Ji Zhang, Han Liu, Tok Wang Ling, Robert M.Bruckner, and A. Min Tjoa
Journal of Database Management (JDM). pp19-40 Volume 17 Issue 3, 2006.
PDF
Canonical Correlation, an Approximation, and the Prediction of Protein Abundance
Anthony Bonner and Han Liu
Proceedings of the Eighth Workshop on Mining Scientific and Engineering Datasets (MSD), 2005.
PDF
A Generalized Real-Time Obstacle Avoidance Method Without the Cspace Calculation
Yong-Ji Wang, Matthew Cartmell, Qiu-Ming Tao, Han Liu
Journal of Computer Science and Technology (JCST), Volume 20(6): 774-787, 2005.
PDF
D-GridMST: Clustering Large Distributed Spatial Databases
Ji Zhang and Han Liu
Book Chapter of Classification and Clustering for Knowledge Discovery. Springer-Verlag Publisher, ISBN 978-3-540-26073-8, 2005.
PDF
Dimension Reduction of Microarray Data with Penalized Independent Component Analysis
Han Liu and Rafal Kustra
The NIPS workshop on New Problems and Methods in Computational Biology (NIPS), 2005.
PDF
Predicting Protein Levels from Tandem Mass Spectrometry Data
Anthony Bonner and Han Liu
The NIPS workshop on New Problems and Methods in Computational Biology (NIPS), 2005.
PDF
Comparison of Discrimination Methods for Peptide Classification in Tandem Mass Spectrometry
Anthony Bonner and Han Liu
IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (IEEE CIBCB), 2004.
PDF
Modeling Protein Tandem Mass Spectrometry Data with an Extended Linear Regression Strategy
Han Liu, Anthony Bonner, and Andrew Emily
The Twenty-sixth Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE EMBC), 2004.
PDF
An Efficient Method to Estimate Labeled Sample Size for Transductive LDA( QDA / MDA) based on the Bayes Risk
Han Liu, Xiaobin Yuan, Qianying Tang, and Rafal Kustra
The Fifteenth European Conference on Machine Learning (ECML'04), 2004.
PDF
A Realistic Method for Real-time Obstacle Avoidance without the Calculation of Cspace Obstacles
Han Liu and Yongji Wang
IEEE International Conference on Robotics and Automaton (IEEE RAM), 2004.
PDF
A Real-time Robot Path Planning Approach without the Computation of Cspace Obstacles
Yongji Wang, Han Liu, Qing Wang, Mingshu Li, Jinhui Zhou and M. Cartmell
Journal of Robotica. pp173-187 Volume 22 Issue 2, 2004.
PDF

Teaching

10-725 (S08) Optimization Theory (graduate course), at the Machine Learning Department, Carnegie Mellon Universitys;
36-625 (S07) Probability and Statistics (graduate course), at the Statistics Department, Carnegie Mellon Universitys;
36-711 (F07) Statistical Computing (graduate course), at the Statistics Department, Carnegie Mellon Universitys;
36-217 (S06, F05) Stochastic Process (ungraduate course), at the Statistics Department, Carnegie Mellon Universitys;
CS-364 (F04) Computational Complexity (undergraduate course), at the Department of Computer Science, University of Toronto;
CS-263 (S04, F03) Theory of Computation (undergraduate course), at the Department of Computer Science, University of Toronto.

Awards and Honors

J. Tinsley Oden Faculty Fellowship, Institute of Computational Engineering and Sciences, University of Texas-Austin, 2010
Best Paper Award, ASA Student Paper Competition in Statistical Computating and GRaphics, American Statistical Association, 2010
Google PHD Fellowship in Statistics, Google Inc, 2009-2011
Best Student Paper Award, The 26th International Conference on Machine Learning, ICML, 2009
Best Overall Paper Award Honorable Mention, The 26th International Conference on Machine Learning, ICML, 2009
Best Paper Award Nomination, The 12th International Conference on Artificial Intelligence and Statistics, AISTATS, 2009
NSF Fund for the "Future Directions in High Dimensional Data Analysis" workshop, Issac Newton Institute, Cambridge, UK, 2008
Carnegie Mellon University Fellowship, Carnegie Mellon University, 2008.

Contact

Gates and Hillman Complex 8008
Carnegie Mellon University

5000 Forbes Ave.
Pittsburgh, PA 15213

Email: hanliu@cs.cmu.edu

Office Phone: 412. 268. 8699