On the Sample Complexity of Graphical Model Selection for Non-Stationary Processes

Abstract

We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed data is modeled as a vector-valued zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This model contains as special cases the standard setting of i.i.d. samples as well as the case of samples forming a stationary or underspread (non-stationary) processes. More generally, our model applies to any process model for which an efficient decorrelation can be obtained. By analyzing a particular model selection method, we derive a sufficient condition on the required sample size for accurate graphical model selection based on non-stationary data.

References in corpus (9)

• Consistency of the group Lasso and multiple kernel learning
• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• Network Lasso: Clustering and Optimization in Large Graphs
• Causal Network Inference via Group Sparse Regularization
• Noncoherent Capacity of Underspread Fading Channels
• Learning Graphical Models With Hubs
• Learning Networks of Stochastic Differential Equations
• Learning the Conditional Independence Structure of Stationary Time Series: A Multitask Learning Approach
• Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso

Cited by in corpus (1)

• When is Network Lasso Accurate: The Vector Case