Theory-independent limits on correlations from generalized Bayesian networks

DOI10.1088/1367-2630/16/11/113043zbMATH Open1451.81028arXiv1405.2572OpenAlexW3106490617WikidataQ62045570 ScholiaQ62045570MaRDI QIDQ3387139FDOQ3387139

Authors: Joe Henson, Raymond Lal, Matthew F. Pusey 

Publication date: 12 January 2021

Published in: New Journal of Physics (Search for Journal in Brave)

Abstract: Bayesian networks provide a powerful tool for reasoning about probabilistic causation, used in many areas of science. They are, however, intrinsically classical. In particular, Bayesian networks naturally yield the Bell inequalities. Inspired by this connection, we generalise the formalism of classical Bayesian networks in order to investigate non-classical correlations in arbitrary causal structures. Our framework of `generalised Bayesian networks' replaces latent variables with the resources of any generalised probabilistic theory, most importantly quantum theory, but also, for example, Popescu-Rohrlich boxes. We obtain three main sets of results. Firstly, we prove that all of the observable conditional independences required by the classical theory also hold in our generalisation; to obtain this, we extend the classical $d$-separation theorem to our setting. Secondly, we find that the theory-independent constraints on probabilities can go beyond these conditional independences. For example we find that no probabilistic theory predicts perfect correlation between three parties using only bipartite common causes. Finally, we begin a classification of those causal structures, such as the Bell scenario, that may yield a separation between classical, quantum and general-probabilistic correlations.

Full work available at URL: https://arxiv.org/abs/1405.2572

Recommendations

• Beyond Bell's theorem. II: Scenarios with arbitrary causal structure
• Bell's local causality is a d-separation criterion
• The lesson of causal discovery algorithms for quantum correlations: causal explanations of Bell-inequality violations require fine-tuning
• Bell correlations and the common future
• Discovering Quantum Causal Models

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Quantum measurement theory, state operations, state preparations (81P15) Quantum coherence, entanglement, quantum correlations (81P40)

Cites Work

• Causality. Models, reasoning, and inference
• Title not available (Why is that?)
• Entropic Inequalities and Marginal Problems
• Causal structures from entropic information: geometry and novel scenarios
• Beyond Bell's theorem: correlation scenarios
• Bell's Inequalities and Density Matrices: Revealing “Hidden” Nonlocality
• Discrete quantum causal dynamics
• Foliable operational structures for general probabilistic theories
• Quantum graphical models and belief propagation
• Independence properties of directed markov fields
• Quantum Bayesian nets
• The operator tensor formulation of quantum theory

Cited In (30)

• Generalization of measurement-induced nonlocality In the bilocal scenario
• Correlations in \(n\)-local scenario
• Polynomial Bell inequalities
• Quantum causal modelling
• Characterizing nonbilocal correlation: a geometric perspective
• Causal inference via string diagram surgery. A diagrammatic approach to interventions and counterfactuals
• Computational tools for solving a marginal problem with applications in Bell non-locality and causal modeling
• Analysing causal structures with entropy
• Margins of discrete Bayesian networks
• Upper bound for variational free energy of Bayesian networks
• Quantifying measurement-induced nonbilocal correlation
• Decomposing all multipartite non-signalling channels via quasiprobabilistic mixtures of local channels in generalised probabilistic theories
• On generalized entropies and information-theoretic Bell inequalities under decoherence
• Beyond Bell's theorem. II: Scenarios with arbitrary causal structure
• The relation between acausality and interference in quantum-like Bayesian networks
• The simplest causal inequalities and their violation
• Bridging the gap between general probabilistic theories and the device-independent framework for nonlocality and contextuality
• A convergent inflation hierarchy for quantum causal structures
• Computation in generalised probabilisitic theories
• Quantum superpositions of ‘common-cause’ and ‘direct-cause’ causal structures
• The sheaf-theoretic structure of definite causality
• Correlations in star networks: from Bell inequalities to network inequalities
• Comment on: ``The notion of locality in relational quantum mechanics
• Categorical probabilistic theories
• The entropic approach to causal correlations
• Characterizing nonclassical correlations of tensorizing states in a bilocal scenario
• A graph-separation theorem for quantum causal models
• Fast tests for probing the causal structure of quantum processes
• Bell's local causality is a d-separation criterion
• Optimal quantum networks and one-shot entropies

This page was built for publication: Theory-independent limits on correlations from generalized Bayesian networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3387139)