Semidefinite Tests for Latent Causal Structures

DOI10.1109/TIT.2019.2935755MaRDI QIDQ5211604zbMATH OpenOpenAlexFDO

Authors

Publication date 28 January 2020

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1701.00652

Mathematics Subject Classification ID

Probabilistic graphical models (62H22) Semidefinite programming (90C22) Applications of graph theory to circuits and networks (94C15)

Abstract: Testing whether a probability distribution is compatible with a given Bayesian network is a fundamental task in the field of causal inference, where Bayesian networks model causal relations. Here we consider the class of causal structures where all correlations between observed quantities are solely due to the influence from latent variables. We show that each model of this type imposes a certain signature on the observable covariance matrix in terms of a particular decomposition into positive semidefinite components. This signature, and thus the underlying hypothetical latent structure, can be tested in a computationally efficient manner via semidefinite programming. This stands in stark contrast with the algebraic geometric tools required if the full observable probability distribution is taken into account. The semidefinite test is compared with tests based on entropic inequalities.

Cited in

(2)

• A convergent inflation hierarchy for quantum causal structures
• Quantum correlation of quantum networks based on their covariance matrices

This page was built for publication: Semidefinite Tests for Latent Causal Structures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5211604)