High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion
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 struct...
Main Authors: | Willsky, Alan S. (Contributor), Tan, Vincent Yan Fu (Contributor), Anandkumar, Animashree (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Laboratory for Information and Decision Systems (Contributor), Massachusetts Institute of Technology. Stochastic Systems Group (Contributor) |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery (ACM),
2013-07-02T18:40:53Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
High-Dimensional Graphical Model Selection: Tractable Graph Families and Necessary Conditions
by: Anandkumar, Animashree, et al.
Published: (2013) -
Feedback Message Passing for Inference in Gaussian Graphical Models
by: Liu, Ying, et al.
Published: (2012) -
Learning Gaussian Tree Models: Analysis of Error Exponents and Extremal Structures
by: Tan, Vincent Yan Fu, et al.
Published: (2011) -
How do the structure and the parameters of Gaussian tree models affect structure learning?
by: Tan, Vincent Yan Fu, et al.
Published: (2011) -
Scaling laws for learning high-dimensional Markov forest distributions
by: Willsky, Alan S., et al.
Published: (2012)