|
|
|
|
| LEADER |
01873 am a22002413u 4500 |
| 001 |
79410 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Willsky, Alan S.
|e author
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
|e contributor
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
|e contributor
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Stochastic Systems Group
|e contributor
|
| 100 |
1 |
0 |
|a Willsky, Alan S.
|e contributor
|
| 100 |
1 |
0 |
|a Tan, Vincent Yan Fu
|e contributor
|
| 100 |
1 |
0 |
|a Anandkumar, Animashree
|e contributor
|
| 700 |
1 |
0 |
|a Tan, Vincent Yan Fu
|e author
|
| 700 |
1 |
0 |
|a Anandkumar, Animashree
|e author
|
| 245 |
0 |
0 |
|a High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion
|
| 260 |
|
|
|b Association for Computing Machinery (ACM),
|c 2013-07-02T18:40:53Z.
|
| 856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/79410
|
| 520 |
|
|
|a We consider the problem of high-dimensional Gaussian graphical model selection. We identify a set of graphs for which an efficient estimation algorithm exists, and this algorithm is based on thresholding of empirical conditional covariances. Under a set of transparent conditions, we establish structural consistency (or sparsistency) for the proposed algorithm, when the number of samples n=omega(J_{min}^{-2} log p), where p is the number of variables and J_{min} is the minimum (absolute) edge potential of the graphical model. The sufficient conditions for sparsistency are based on the notion of walk-summability of the model and the presence of sparse local vertex separators in the underlying graph. We also derive novel non-asymptotic necessary conditions on the number of samples required for sparsistency.
|
| 546 |
|
|
|a en_US
|
| 655 |
7 |
|
|a Article
|
| 773 |
|
|
|t Journal of Machine Learning Research
|
