DeepAI AI Chat
Log In Sign Up

Approximate Implication with d-Separation

by   Batya Kenig, et al.

The graphical structure of Probabilistic Graphical Models (PGMs) encodes the conditional independence (CI) relations that hold in the modeled distribution. Graph algorithms, such as d-separation, use this structure to infer additional conditional independencies, and to query whether a specific CI holds in the distribution. The premise of all current systems-of-inference for deriving CIs in PGMs, is that the set of CIs used for the construction of the PGM hold exactly. In practice, algorithms for extracting the structure of PGMs from data, discover approximate CIs that do not hold exactly in the distribution. In this paper, we ask how the error in this set propagates to the inferred CIs read off the graphical structure. More precisely, what guarantee can we provide on the inferred CI when the set of CIs that entailed it hold only approximately? It has recently been shown that in the general case, no such guarantee can be provided. We prove that such a guarantee exists for the set of CIs inferred in directed graphical models, making the d-separation algorithm a sound and complete system for inferring approximate CIs. We also prove an approximation guarantee for independence relations derived from marginal CIs.


page 1

page 2

page 3

page 4


Identifying Independence in Relational Models

The rules of d-separation provide a framework for deriving conditional i...

Local Exchangeability

Exchangeability---in which the distribution of an infinite sequence is i...

On perfectness in Gaussian graphical models

Knowing when a graphical model is perfect to a distribution is essential...

Hereditary rigidity, separation and density In memory of Professor I.G. Rosenberg

We continue the investigation of systems of hereditarily rigid relations...

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

We introduce and study the neighbourhood lattice decomposition of a dist...

The Geometry of Gaussoids

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

Using the structure of d-connecting paths as a qualitative measure of the strength of dependence

Pearls concept OF a d - connecting path IS one OF the foundations OF the...