Optimal estimation of Gaussian DAG models

01/25/2022
by   Ming Gao, et al.
0

We study the optimal sample complexity of learning a Gaussian directed acyclic graph (DAG) from observational data. Our main results establish the minimax optimal sample complexity for learning the structure of a linear Gaussian DAG model in two settings of interest: 1) Under equal variances without knowledge of the true ordering, and 2) For general linear models given knowledge of the ordering. In both cases the sample complexity is n≍ qlog(d/q), where q is the maximum number of parents and d is the number of nodes. We further make comparisons with the classical problem of learning (undirected) Gaussian graphical models, showing that under the equal variance assumption, these two problems share the same optimal sample complexity. In other words, at least for Gaussian models with equal error variances, learning a directed graphical model is statistically no more difficult than learning an undirected graphical model. Our results also extend to more general identification assumptions as well as subgaussian errors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2021

Symmetries in Directed Gaussian Graphical Models

We define Gaussian graphical models on directed acyclic graphs with colo...
research
07/15/2017

Learning linear structural equation models in polynomial time and sample complexity

The problem of learning structural equation models (SEMs) from data is a...
research
08/31/2023

Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs

In this article, the optimal sample complexity of learning the underlyin...
research
06/10/2018

Identifiability in Gaussian Graphical Models

In high-dimensional graph learning problems, some topological properties...
research
02/20/2020

Learning Gaussian Graphical Models via Multiplicative Weights

Graphical model selection in Markov random fields is a fundamental probl...
research
06/04/2023

Optimal neighbourhood selection in structural equation models

We study the optimal sample complexity of neighbourhood selection in lin...
research
11/03/2017

Partial correlation graphs and the neighborhood lattice

We define and study partial correlation graphs (PCGs) with variables in ...

Please sign up or login with your details

Forgot password? Click here to reset