# Precision matrix estimation

## Especially Gaussain

Estimating the thing that is given to you by oracles in statistics homework assignments: the covariance matrix or its inverse, the precision matrices. Or, if you data is indexed in some fashion, the covariance kernel. We are especially interested in this in Gaussian processes, where the covariance kernel characterises the process up to its mean.

I am not introducing a complete theory of covariance estimation here, merely mentioning a couple of tidbits for future reference.

Two big data problems problems can arise here: large $$p$$ (ambient dimension) and large $$n$$ (sample size). Large $$p$$ is a problem because the covariance matrix is a $$p \times p$$ matrixand frequently we need to invert it to calculate some target estimand.

Often life can be made not too bad for large $$n$$ with Gaussian structure because, essentially, it has a nice exponential family structure and hence has sufficient statistics.

## The obvious way

Estimate the covariance matrix then invert it. This is the baseline. 🏗

## Bayesian

🏗 Wishart priors?

## References

Aragam, Bryon, Jiaying Gu, and Qing Zhou. 2017. arXiv:1703.04025 [Cs, Stat], March.
Avagyan, Vahe, and Xiaoling Mei. 2022. Communications in Statistics - Simulation and Computation 51 (4): 1381–1400.
Chen, Xiaohui, Mengyu Xu, and Wei Biao Wu. 2013. The Annals of Statistics 41 (6).
Fan, Jianqing, Yuan Liao, and Han Liu. 2016. The Econometrics Journal 19 (1): C1–32.
Hsieh, Cho-Jui, Mátyás A. Sustik, Inderjit S. Dhillon, and Pradeep D. Ravikumar. 2014. Journal of Machine Learning Research 15 (1): 2911–47.
Hsieh, Cho-Jui, Mátyás A. Sustik, Inderjit S. Dhillon, Pradeep Ravikumar, and Russell A. Poldrack. 2013. In Advances in Neural Information Processing Systems, 16. NIPS’13. Red Hook, NY, USA: Curran Associates Inc.
Janková, Jana, and Sara van de Geer. 2015. arXiv:1507.02061 [Math, Stat], July.
Khoshgnauz, Ehsan. 2012. arXiv:1206.6361 [Cs, Stat], June.
Kuismin, Markku O., and Mikko J. Sillanpää. 2017. WIREs Computational Statistics 9 (6): e1415.
Lam, Clifford, and Jianqing Fan. 2009. Annals of Statistics 37 (6B): 4254–78.
Le, Thien-Minh, and Ping-Shou Zhong. 2021. arXiv.
Meier, Alexander, Claudia Kirch, and Renate Meyer. 2020. Journal of Multivariate Analysis 175 (January): 104560.
Moscone, Francesco, Elisa Tosetti, and Veronica Vinciotti. 2017. The Econometrics Journal 20 (3): S61–85.
Pleiss, Geoff, Jacob R. Gardner, Kilian Q. Weinberger, and Andrew Gordon Wilson. 2018. In. arXiv.
Pourahmadi, Mohsen. 2011. Statistical Science 26 (3): 369–87.
Saad, Yousef. 2003. Iterative Methods for Sparse Linear Systems: Second Edition. 2nd ed. SIAM.
Ubaru, Shashanka, Jie Chen, and Yousef Saad. 2017. SIAM Journal on Matrix Analysis and Applications 38 (4): 1075–99.
Wang, Lingxiao, Xiang Ren, and Quanquan Gu. n.d. “Precision Matrix Estimation in High Dimensional Gaussian Graphical Models with Faster Rates,” 9.
Wu, Wei Biao, and Mohsen Pourahmadi. 2003. Biometrika 90 (4): 831–44.
Yuan, Ming. 2010. “High Dimensional Inverse Covariance Matrix Estimation via Linear Programming.” The Journal of Machine Learning Research 11: 26.
Zhang, T., and H. Zou. 2014. Biometrika 101 (1): 103–20.

### No comments yet. Why not leave one?

GitHub-flavored Markdown & a sane subset of HTML is supported.