• Corpus ID: 7650573

Segregated Graphs and Marginals of Chain Graph Models

  title={Segregated Graphs and Marginals of Chain Graph Models},
  author={Ilya Shpitser},
  • I. Shpitser
  • Published in NIPS 7 December 2015
  • Computer Science
Bayesian networks are a popular representation of asymmetric (for example causal) relationships between random variables. Markov random fields (MRFs) are a complementary model of symmetric relationships used in computer vision, spatial modeling, and social and gene expression networks. A chain graph model under the Lauritzen-Wermuth-Frydenberg interpretation (hereafter a chain graph model) generalizes both Bayesian networks and MRFs, and can represent asymmetric and symmetric relationships… 

Figures from this paper

Identification and Estimation of Causal Effects from Dependent Data

A general theory describing when causal inferences are possible in non-iid contexts is developed and how statistical inference may be performed on causal parameters identified by this algorithm is demonstrated.

Relational Causal Models with Cycles: Representation and Reasoning

This work shows the necessary and sufficient conditions for the completeness of σ -AGG and that relational ρ -separation is sound and complete in the presence of one or more cycles with arbitrary length, and introduces a new lifted representation, �x - abstract ground graph which helps with abstracting statistical independence relations in all possible instantiations of the cyclic relational model.

Unifying Gaussian LWF and AMP Chain Graphs to Model Interference

  • J. Peña
  • Computer Science
    Journal of Causal Inference
  • 2019
This paper defines a new class of causal models that can represent both interference and non-interference relationships for Gaussian distributions, and introduces global and local and pairwise Markov properties for them and proves their equivalence.

Unifying DAGs and UGs

  • J. Peña
  • Computer Science, Mathematics
  • 2018
We introduce a new class of graphical models that generalizes Lauritzen-Wermuth-Frydenberg chain graphs by relaxing the semi-directed acyclity constraint so that only directed cycles are forbidden.

Identification in Causal Models With Hidden Variables.

  • I. Shpitser
  • Economics
    Journal de la Societe francaise de statistique
  • 2020
Targets of inference that establish causality are phrased in terms of counterfactual responses to interventions. These potential outcomes operationalize cause effect relationships by means of

A Survey on Causal Inference

This survey provides a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks, and presents the plausible applications of these methods, including the applications in advertising, recommendation, medicine, and so on.

General Identification of Dynamic Treatment Regimes Under Interference

This paper formalizes a variety of policy interventions under interference and extends existing identification theory and illustrates the efficacy of policy maximization under interference in a simulation study.

Marrying Fairness and Explainability in Supervised Learning

This work formalizes direct discrimination as a direct causal effect of the protected attributes on the decisions, while induced discrimination is formalized as a change in the causal influence of non-protected features associated with theprotected attributes.

Ananke: A Python Package For Causal Inference Using Graphical Models

A broad overview of the Ananke package, an object-oriented Python package for causal inference with graphical models, and example usage for a problem with unmeasured confounding are presented.

OcéanIA: AI, Data, and Models for Understanding the Ocean and Climate Change

  • Environmental Science
  • 2021



Bayesian Networks from the Point of View of Chain Graphs

The paper gives a few arguments in favour of use of chain graphs for description of probabilistic conditional independence structures and a separation criterion for reading independences from a chain graph is formulated.

Discrete chain graph models

The statistical literature discusses different types of Markov properties for chain graphs that lead to four possible classes of chain graph Markov models. The different models are rather well

A characterization of Markov equivalence classes for acyclic digraphs

Undirected graphs and acyclic digraphs (ADGs), as well as their mutual extension to chain graphs, are widely used to describe dependencies among variables in multivariate distributions. In


A set of independence statements may define the independence structure of interest in a family of joint probability distributions. This structure is often captured by a graph that consists of nodes

Chain graph models and their causal interpretations

Chain graphs are a natural generalization of directed acyclic graphs and undirected graphs. However, the apparent simplicity of chain graphs belies the subtlety of the conditional independence

Markovian acyclic directed mixed graphs for discrete data

Acyclic directed mixed graphs (ADMGs) are graphs that contain directed ($\rightarrow$) and bidirected ($\leftrightarrow$) edges, subject to the constraint that there are no cycles of directed edges.

Markov properties for mixed graphs

In this paper, we unify the Markov theory of a variety of different types of graphs used in graphical Markov models by introducing the class of loopless mixed graphs, and show that all independence

Ancestral graph Markov models

A class of graphical independence models that is closed under marginalization and conditioning but that contains all DAG independence models, called maximal ancestral graphs, which lead to a simple parametrization of the corresponding set of distributions in the Gaussian case.

Marginalizing and conditioning in graphical models

A class of graphs is introduced which is closed under marginalizing and conditioning. It is shown that these operations can be executed by performing in arbitrary order a sequence of simple, strictly

Causal Inference for Networks

Suppose that we observe a population of causally connected units according to a network. On each unit we observe a set of potentially connected units that contains the true connections, and a