Office: 445B West Hall
Mailing: 439 West Hall
1085 South University Ave.
Ann Arbor, MI 48109
Most of my recent papers are on
Publications by Year/ Publications by Area/ Google Scholar /CV
Annotated Bibliography on early-stage research work (now outdated)
The concentration of measure phenomenon on sparse matrix variate random matrices
Working paper, 2017.
Non-separable covariance models for spatio-temporal data, with applications to neural encoding analysis
Seyoung Park, Kerby Shedden and Shuheng Zhou. Submitted, 2017
The tensor graphical Lasso (TeraLasso)
Kristjan Greenewald, Shuheng Zhou and Alfred Hero. Submitted, 2017
Joint mean and covariance estimation with unreplicated matrix-variate data
Journal of the American Statistical Association (Theory and Method), Forthcoming, 2018.
Michael Hornstein, Roger Fan, Kerby Shedden, and Shuheng Zhou.
Time-dependent spatially varying graphical models, with application to brain fMRI data analysis
Advances in Neural Information Processing Systems 30 (NIPS 2017). Rate of acceptance: 20.9%
Kristjan Greenewald, Seyoung Park, Shuheng Zhou, and Alexander Giessing
conf link/ [pdf] /arxiv
Dantzig-type penalization for multiple quantile regression with high dimensional covariates
Statistica Sinica, Vol. 27, No. 4, 1619-1638, October 2017.
Seyoung Park, Xuming He, and Shuheng Zhou.
The Bigraphical Lasso
Proceedings of the 30th International Conference on Machine Learning, Atlanta, Georgia, USA,(ICML 2013).
Alfredo Kalaitzis, John Lafferty, Neil Lawrence, and Shuheng Zhou
conf link/ [pdf]/ Supplementary material
On convergence of Kronecker graphical Lasso algorithms
IEEE Transactions on Signal Processing, Vol. 61. No 7, 1743--1755, 2013.
Theodoros Tsiligkaridis, Alfred Hero, and Shuheng Zhou.
Journal Link / [pdf]
High-dimensional covariance estimation based on Gaussian graphical models
Journal of Machine Learning Research, Vol. 12, 2975-3026, 2011.
With Philipp Rütimann, Min Xu, and Peter Bühlmann.
Journal Link/ [pdf]
The adaptive and the thresholded Lasso for potentially misspecified models (and a lower bound for the Lasso)
Electronic Journal of Statistics 2011, Vol. 5, 688-749.
With Sara van de Geer and Peter Bühlmann. Journal Link
A statistical framework for differential privacy
Journal of the American Statistical Association, Vol. 105, No. 489, 375--389, 2010.
With Larry Wasserman. [pdf] / Appeared as a featured JASA article.
Time varying undirected graphs
Machine Learning Journal, Vol. 80, Numbers 2--3, 295--319, 2010 (invited), special issue for COLT 2008.
With John Lafferty and Larry Wasserman.
Journal Link/ [pdf]/ conf version
Thresholding procedures for high dimensional variable selection and statistical estimation
Advances in Neural Information Processing Systems 22 (NIPS), 2304--2312, December 2009.
conf link/ [pdf] For full proofs see arxiv:1002.1583.
Compressed and privacy sensitive sparse regression
Transactions on Information Theory, Vol. 55, No.2, 846--866, February 2009.
With John Lafferty and Larry Wasserman.
Journal Link/ [PDF] / conf version/ arxiv:0706.0534
Differential privacy with compression
International Symposium on Information Theory (ISIT).Seoul, Korea, June -- July 2009.
Shuheng Zhou, Katrina Ligett, and Larry Wasserman.
A rigorous analysis of population stratification with limited data
with Kamalika Chaudhuri, Eran Halperin, and Satish Rao.
In ACM-SIAM Symposium on Discrete Algorithms (SODA) 2007,
New Orleans, Louisiana. January 2007.PDF
Thresholded Lasso for high dimensional variable selection
Technical Report 511, Department of Statistics, University of Michigan. 2010.
arxiv:1002.1583 / [pdf] /Talk slides, Universite de Paris Est Marne-la-Vallee, May 20, 2010.
Adaptive Lasso for high dimensional regression and Gaussian graphical modeling
Shuheng Zhou, Sara van de Geer, and Peter Bühlmann. March 2009.
arxiv:0903.2515. Note: Part of this paper was superseded by arxiv:1001.5176.
Please cite our EJS paper in Vol. 5, 688-749, 2011.
Restricted eigenvalue conditions on subgaussian random matrices
Note: Results are weaker than those in a subsequent paper arxiv:1106.1151
not intended for publication; However, proofs are rather different and quite short.
Last updated: 11/26/2017 @Copyright by Shuheng Zhou, 2010 - 2018, all rights reserved