Bounding Classical and Quantum Correlations in Bayesian Networks with Quasiprobabilities

• URL: http://arxiv.org/abs/2606.23372v1
• Date: Mon, 22 Jun 2026 14:07:33 GMT
• Title: Bounding Classical and Quantum Correlations in Bayesian Networks with Quasiprobabilities
• Abstract summary: We consider quasiprobabilistic models for Bayesian networks.<n>We denote the set of correlations resulting from these models as the quasi set.<n>We show a generalisation of this result for a broad class of networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bell's theorem reveals that quantum theory is in tension with classical causal reasoning and, in particular, the notion of local causality. This is now understood as a particular example of non-classicality in the study of correlations in (Bayesian) networks with both unobserved and observed nodes: the correlations are probability distributions over the observed nodes. There is a great deal of work aiming to understand the bounds on quantum and classical correlations in such networks and one approach is to consider outer approximations to the former. Along these lines, we consider quasiprobabilistic models for Bayesian networks, which can be seen as classical models but the probability distributions involving unobserved nodes are "replaced" with quasiprobabilities that respect normalisation but not positivity. We denote the set of correlations resulting from these models as the quasi set. Such models have a history in the study of Bell-type non-classicality where it has been shown that they can produce all non-signalling correlations. We show a generalisation of this result for a broad class of networks, which motivates a conjecture that the quasi set recovers the so called nested Markov model. Our work utilises a connection to tensor network decompositions, which may be of independent interest.

Related papers

• "Train classical, deploy quantum" requires rethinking generalization [42.16343861129583]
  We benchmark a broad set of quantum and classical generative models by direct sampling.<n>We show that models trained with a moment-matching loss generally show worse generalization than the likelihood-trained models.
  arXiv  Detail & Related papers  (2026-08-31T17:26:27Z)
• Playing Nonlocal Games with Little to No Shared Randomness [7.306738257366766]
  Bell nonlocality reveals correlations that cannot be explained by classical models.<n>We show that these correlations give rise to an entropic Bell bipartite limited scenarios.
  arXiv  Detail & Related papers  (2026-08-08T00:38:27Z)
• A quantum model of opinion dynamics on networks [0.0]
  We propose a quantum model of opinion dynamics in which each agent's cognitive state is represented by a density matrix.<n>We test the framework on synthetic and real-world networks and observe that pairwise correlations follow network-dependent transient dynamics.
  arXiv  Detail & Related papers  (2026-07-01T20:19:12Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• On the Significance of Intermediate Latents: Distinguishing Quantum Causal Scenarios with Indistinguishable Classical Analogs [1.03590082373586]
  We consider directed acyclic graphs each of which contains both nodes representing observed variables as well as nodes representing latent or hidden variables.<n>We highlight how the change to a quantum interpretation of the latent nodes induces distinctions between causal scenarios that would be classically indistinguishable.
  arXiv  Detail & Related papers  (2024-12-13T16:08:30Z)
• Estimating the volumes of correlations sets in causal networks [0.41942958779358674]
  Causal networks beyond that in paradigmatic Bell's theorem can lead to new kinds and applications of non-classicality. We show where the most disseminated tool in the community, is unable to detect a significant portion of the non-classical behaviors. We also show that the use interventions, a central tool in inference, can substantially our ability to witness non-classicality.
  arXiv  Detail & Related papers  (2023-11-14T22:35:57Z)
• Generalized Bell scenarios: disturbing consequences on local-hidden-variable models [0.0]
  Bell nonlocality and Kochen-Specker contextuality are among the main topics of foundations of quantum theory. This article reviews, expands and obtains new results regarding a unified framework for these phenomena.
  arXiv  Detail & Related papers  (2023-07-29T19:37:22Z)
• Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures [93.17009514112702]
  Pruning, setting a significant subset of the parameters of a neural network to zero, is one of the most popular methods of model compression. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood.
  arXiv  Detail & Related papers  (2023-04-25T07:42:06Z)
• Work statistics, quantum signatures and enhanced work extraction in quadratic fermionic models [62.997667081978825]
  In quadratic fermionic models we determine a quantum correction to the work statistics after a sudden and a time-dependent driving. Such a correction lies in the non-commutativity of the initial quantum state and the time-dependent Hamiltonian. Thanks to the latter, one can assess the onset of non-classical signatures in the KDQ distribution of work.
  arXiv  Detail & Related papers  (2023-02-27T13:42:40Z)
• Causal networks and freedom of choice in Bell's theorem [0.7637291629898925]
  We show that the level of measurement dependence can be quantitatively upper bounded if we arrange the Bell test within a network. We also prove that these results can be adapted in order to derive non-linear Bell inequalities for a large class of causal networks.
  arXiv  Detail & Related papers  (2021-05-12T15:14:17Z)
• Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition [34.235007566913396]
  We describe an interpretable, symmetric decomposition of the variance into terms associated with the labels. We find that the bias decreases monotonically with the network width, but the variance terms exhibit non-monotonic behavior. We also analyze the strikingly rich phenomenology that arises.
  arXiv  Detail & Related papers  (2020-11-04T21:04:02Z)
• Emergence of classical behavior in the early universe [68.8204255655161]
  Three notions are often assumed to be essentially equivalent, representing different facets of the same phenomenon. We analyze them in general Friedmann-Lemaitre- Robertson-Walker space-times through the lens of geometric structures on the classical phase space. The analysis shows that: (i) inflation does not play an essential role; classical behavior can emerge much more generally; (ii) the three notions are conceptually distinct; classicality can emerge in one sense but not in another.
  arXiv  Detail & Related papers  (2020-04-22T16:38:25Z)
• Rethinking Bias-Variance Trade-off for Generalization of Neural Networks [40.04927952870877]
  We provide a simple explanation for this by measuring the bias and variance of neural networks. We find that variance unimodality occurs robustly for all models we considered. Deeper models decrease bias and increase variance for both in-distribution and out-of-distribution data.
  arXiv  Detail & Related papers  (2020-02-26T07:21:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.