Log In Sign Up

Support Union Recovery in Meta Learning of Gaussian Graphical Models

by   Qian Zhang, et al.

In this paper we study Meta learning of Gaussian graphical models. In our setup, each task has a different true precision matrix, each with a possibly different support (i.e., set of edges in the graph). We assume that the union of the supports of all the true precision matrices (i.e., the true support union) is small in size, which relates to sparse graphs. We propose to pool all the samples from different tasks, and estimate a single precision matrix by ℓ_1-regularized maximum likelihood estimation. We show that with high probability, the support of the estimated single precision matrix is equal to the true support union, provided a sufficient number of samples per task n ∈ O((log N)/K), for N nodes and K tasks. That is, one requires less samples per task when more tasks are available. We prove a matching information-theoretic lower bound for the necessary number of samples, which is n ∈Ω((log N)/K), and thus, our algorithm is minimax optimal. Synthetic experiments validate our theory.


page 1

page 2

page 3

page 4


Meta Sparse Principal Component Analysis

We study the meta-learning for support (i.e. the set of non-zero entries...

On the Statistical Efficiency of ℓ_1,p Multi-Task Learning of Gaussian Graphical Models

In this paper, we present ℓ_1,p multi-task structure learning for Gaussi...

Learning Some Popular Gaussian Graphical Models without Condition Number Bounds

Gaussian Graphical Models (GGMs) have wide-ranging applications in machi...

On the Sample Complexity of Learning Graphical Games

We analyze the sample complexity of learning graphical games from purely...

Efficient Statistics for Sparse Graphical Models from Truncated Samples

In this paper, we study high-dimensional estimation from truncated sampl...

Asymptotic normality and optimalities in estimation of large Gaussian graphical models

The Gaussian graphical model, a popular paradigm for studying relationsh...

Learning to Discover Sparse Graphical Models

We consider structure discovery of undirected graphical models from obse...