DeepAI AI Chat
Log In Sign Up

A non-graphical representation of conditional independence via the neighbourhood lattice

by   Arash A. Amini, et al.

We introduce and study the neighbourhood lattice decomposition of a distribution, which is a compact, non-graphical representation of conditional independence that is valid in the absence of a faithful graphical representation. The idea is to view the set of neighbourhoods of a variable as a subset lattice, and partition this lattice into convex sublattices, each of which directly encodes a collection of conditional independence relations. We show that this decomposition exists in any compositional graphoid and can be computed efficiently and consistently in high-dimensions. In particular, this gives a way to encode all of independence relations implied by a distribution that satisfies the composition axiom, which is strictly weaker than the faithfulness assumption that is typically assumed by graphical approaches. We also discuss various special cases such as graphical models and projection lattices, each of which has intuitive interpretations. Along the way, we see how this problem is closely related to neighbourhood regression, which has been extensively studied in the context of graphical models and structural equations.


page 1

page 2

page 3

page 4


Decomposable context-specific models

We introduce a family of discrete context-specific models, which we call...

Graphical models for circular variables

Graphical models are a key class of probabilistic models for studying th...

Partial correlation graphs and the neighborhood lattice

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

Conditional Independence Beyond Domain Separability: Discussion of Engelke and Hitz (2020)

We congratulate Engelke and Hitz on a thought-provoking paper on graphic...

Lattice Conditional Independence Models and Hibi Ideals

Lattice Conditional Independence models are a class of models developed ...

The Geometry of Gaussoids

A gaussoid is a combinatorial structure that encodes independence in pro...

Approximate Implication with d-Separation

The graphical structure of Probabilistic Graphical Models (PGMs) encodes...