Embedded Files
I am Professor of Statistics at the University of California, Riverside. My research spans high dimensional statistics, machine learning, algorithms and privacy.
Teaching | Publications by year | Bio
email: szhou@ucr.edu
Selected Preprints
S. Zhou. Semidefinite programming relaxations and debiasing for MAXCUT-based clustering. Submitted, 2025. 86 pages. pdf
This paper combines two arXiv preprints:
Semidefinite programming on population clustering: a global analysis. January 2023. pdf
Debiasing and a local analysis for population clustering using semidefinite programming. January 2024. This paper supersedes an earlier version dated Nov. 2023. pdf
My 6th grader asked Gemini Deep Research to summarize "Semidefinite programming relaxations and debiasing for MAXCUT-based clustering" based on arXiv versions. Posted here is a gently scrutinized version to eliminate some speculations from Section 4.1.
S. Zhou and K. Greenewald. Finite sample rates of convergence for the Bigraphical and Tensor graphical Lasso estimators. preprint arXiv pdf
Selected Journal Papers
Selected Journal Papers
The authors on theory papers are alphabetically listed
Directly supervised students are underlined.
Statistics Theory and Methodology
S. Zhou. Thresholded Lasso for high dimensional variable selection. Annals of the Institute of Statistical Mathematics, Published Online December, 2025. Preliminary abstract appeared in Advances in Neural Information Processing Systems 22. Preprint /Online Version
S. Zhou. Concentration of measure bounds for matrix-variate data with missing values. Bernoulli 30(1), pp 198–226, 2024. Originally posted on arXiv 2008.03244 titled "The tensor quadratic forms" (71 Pages), August 2020. pdf/ Journal Link.
K. Greenewald, S. Zhou, and A. Hero. The tensor graphical Lasso (TeraLasso). Journal of Royal Statistical Society, Series B 81 (5), pp 901--931, 2019. pdf /Journal Link
M. Hornstein, R. Fan, K. Shedden, and S. Zhou. Joint mean and covariance estimation with unreplicated matrix-variate data. Journal of the American Statistical Association, Vol. 114 (526), pp 682--696, 2019. pdf / R package
S. Zhou. Sparse Hanson-Wright inequalities for subgaussian quadratic forms. Bernoulli, Vol. 25 (3), pp 1603--1639, 2019. pdf
M. Rudelson and S. Zhou. Errors-in-variables models with dependent measurements. Electronic Journal of Statistics, Vol. 11 (1), pp 1699--1797, 2017. pdf
S. Zhou. Gemini: Graph estimation with matrix variate normal instances. Annals of Statistics, Vol. 42 (2), pp 532--562, 2014. Journal Link
M. Rudelson and S. Zhou. Reconstruction from anisotropic random measurements. IEEE Transactions on Information Theory, Vol. 59. (6), pp 3434--3447, 2013. pdf / talk slides
T. Tsiligkaridis, A. Hero, and S. Zhou. On convergence of Kronecker graphical Lasso algorithms. IEEE Transactions on Signal Processing ,Vol. 61 (7), pp 1743–1755, 2013. pdf
S. Zhou, P. Rutimann, M. Xu, and P. Bühlmann. High-dimensional covariance estimation based on Gaussian graphical models. Journal of Machine Learning Research, Vol. 12 (91), pp 2975--3026, 2011. pdf / Journal Link
S. van de Geer, P. Bühlmann, and S. Zhou. 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. Journal Link
L. Wasserman and S. Zhou. A Statistical framework for differential privacy. Journal of the American Statistical Association, Vol. 105 (489), pp 375--389, 2010 (Appeared as a featured article). pdf
S. Zhou, J. Lafferty, and L. Wasserman. Time varying undirected graphs. Machine Learning Journal, Vol 80, Numbers 2--3, pp 295--319, 2010 (Invited and peer reviewed; Special Issue on Learning Theory). pdf
S. Zhou, J. Lafferty, and L. Wasserman. Compressed and privacy sensitive sparse regression. IEEE Transactions on Information Theory, Vol. 55 (2), pp 846--866, 2009. Preliminary abstract appeared in Advances in Neural Information Processing Systems (NIPS) 20. pdf
Theoretical Computer Science
T.H. Chan, A. Gupta, B.M. Maggs and S. Zhou. On hierarchical routing in doubling metrics. ACM Transactions on Algorithms (TALG) Vol. 12 (4), pp 1--22, 2016. pdf
S. Rao and S. Zhou. Edge disjoint paths in moderately connected graphs. SIAM Journal on Computing, Vol. 39 (5), pp 1856--1887, 2010. Journal version
A. Blum, A. Coja-Oghlan, A. Frieze and S. Zhou. Separating populations with wide data: a spectral analysis. Electronic Journal of Statistics, Vol. 3, pp 76--113, 2009. Journal Link
Software Package
Michael Hornstein, Roger Fan, Kerby Shedden and Shuheng Zhou. “jointMeanCov: Joint Mean and Covariance Estimation for Matrix-Variate Data.” The Comprehensive R Archive Network. http://cran.r-project.org. Available since 2019. This package contains algorithms and functions for jointly estimating two-group means and covariances for matrix-variate data and calculating test statistics.
## How to Cite
Please acknowledge the development team by citing the following paper:
M. Hornstein, R. Fan, K. Shedden, and S. Zhou. Joint mean and covariance estimation with unreplicated matrix-variate data. Journal of the American Statistical Association, Vol. 114 (526), pp 682--696, 2019
Note: You are welcome to cite the original Gemini paper regarding the underlying methodology, but please ensure the paper above is included to credit the implementation team.
Selected Conference Papers (Machine Learning)
Directly supervised students are underlined.
S. Zhou and K. Greenewald. Sharper rates of convergence for the tensor graphical Lasso estimator. Proceedings of 2024 IEEE International Symposium on Information Theory (ISIT 2024), Pages 533-588. Athens, Greece. pdf / link
R. Fan, B. Jang, Y. Sun, and S. Zhou. Precision matrix estimation with noisy and missing data. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 89:2810–2819, 2019. Link
K. Greenewald, S. Park, S. Zhou, and A. Giessing. Time-dependent spatially varying graphical models, with application to brain fMRI data analysis. Advances in Neural Information Processing Systems 30, 2017. pdf
A. Kalaitzis, J. Lafferty, N. D. Lawrence, and S. Zhou. The Bigraphical Lasso. Proceedings of the 30th International Conference on Machine Learning (ICML), PMLR 28(3):1229–1237, 2013. Link
S. Zhou. Thresholding procedures for high dimensional variable selection and statistical estimation. Advances in Neural Information Processing Systems 22, Pages 2304–2312, 2009. pdf
S. Zhou, K. Ligett, L. Wasserman. Differential privacy with compression. Proceedings of 2009 IEEE International Symposium on Information Theory, Seoul, Korea, 2009. Preprint arXiv:0901.1365 / Link
Selected Talks
Selected Talks
Tensor graphical models for complex and high dimensional data. Algorithmic Advances for Statistical Inference with Combinatorial Structure, Simons Institute for the Theory of Computing, Berkeley, CA, Oct. 11-15, 2021. Abstract, Video
Reconstruction from anisotropic random measurements. Coding, Complexity, and Sparsity Workshop (SPARC), University of Michigan, Ann Arbor, MI, August 5-7, 2013. slides
High-dimensional covariance estimation based on Gaussian graphical models. IMA workshop on High Dimensional Phenomena, University of Minnesota, Minneapolis, MN, September 2011. slides
Thresholded Lasso for high dimensional variable selection. Probability and Geometry in High Dimensions, Université Paris-Est Marne-la-Vallée, May 2010. slides
Google Sites
Report abuse