2. (sparse) GGMのモチベーション
• Large p, small n problem
– 正則化のため低次元構造を課すのが一般的
アプローチ(Negahban et al. 2012)
• ガウス分布データにおける中心的問題は
inverse covariance matrix(精度行列)
の推定
観測
サンプル数 n
データの次元数p
15. References
1. Lauritzen, S.L. Graphical models, volume 17. Oxford University Press, USA,
1996.
2. Ravikumar, Pradeep, Wainwright, Martin J, Raskutti, Garvesh, and Yu, Bin. High-
dimensional covariance estimation by minimizing l1-penalized log-determinant
di- vergence. Electronic Journal of Statistics, 5:935-980, 2011.
3. Chandrasekaran, Venkat, Parrilo, Pablo A, and Willsky, Alan S. Latent variable
graphical model selection via convex optimization. Annals of Statistics,
40(4):1935-1967, 2012.
4. Friedman, Jerome, Hastie, Trevor, and Tibshirani, Robert. Sparse inverse
covariance estimation with the graphical lasso. Biostatistics, 9(3):432-441, 2008.
5. Rothman, Adam J, Bickel, Peter J, Levina, Elizaveta, and Zhu, Ji. Sparse
permutation invariant covariance estimation. Electronic Journal of Statistics,
2:494-515, 2008.
6. Choi, Myung Jin, Chandrasekaran, Venkat, and Willsky, Alan S. Gaussian
multiresolution models: Exploiting sparse Markov and covariance structure.
Signal Processing, IEEE Transactions on, 58(3):1012-1024, 2010.
7. Choi, Myung Jin, Tan, Vincent YF, Anandkumar, Animashree, and Willsky, Alan
S. Learning latent tree graphical models. Journal of Machine Learning Research,
12:1729-1770, 2011.
8. Ma, Shiqian, Xue, Lingzhou, and Zou, Hui. Alternating direction methods for
latent variable Gaussian graphical model selection. Neural computation,
25(8):2172-2198, 2013.