Duality of graphical models and tensor networks

DOI10.1093/IMAIAI/IAY009MaRDI QIDQ5006492zbMATH OpenOpenAlexWikidataFDO

Authors Elina Robeva, Anna Leah Seigal

Publication date 16 August 2021

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1710.01437

zbMATH Keywords

belief propagationgraphical modelshypergraphstensor networks

Mathematics Subject Classification ID

Hypergraphs (05C65) Small world graphs, complex networks (graph-theoretic aspects) (05C82) Quantum computation (81P68)

Abstract: In this article we show the duality between tensor networks and undirected graphical models with discrete variables. We study tensor networks on hypergraphs, which we call tensor hypernetworks. We show that the tensor hypernetwork on a hypergraph exactly corresponds to the graphical model given by the dual hypergraph. We translate various notions under duality. For example, marginalization in a graphical model is dual to contraction in the tensor network. Algorithms also translate under duality. We show that belief propagation corresponds to a known algorithm for tensor network contraction. This article is a reminder that the research areas of graphical models and tensor networks can benefit from interaction.

Recommendations

• On the geometry of tensor network states
• Tensor networks and the enumerative geometry of graphs
• Tensor networks in machine learning
• Contraction of matchgate tensor networks on non-planar graphs
• scientific article; zbMATH DE number 922429

Cited in

(19)

• The linear span of uniform matrix product states
• The set of orthogonal tensor trains
• Lower bounds on the rank and symmetric rank of real tensors
• On some general operators of hypergraphs
• Contraction of matchgate tensor networks on non-planar graphs
• scientific article; zbMATH DE number 922429 (Why is no real title available?)
• Investigation of commuting Hamiltonian in quantum Markov network
• scientific article; zbMATH DE number 7626702 (Why is no real title available?)
• Tensor network complexity of multilinear maps
• Orthogonal decomposition of tensor trains
• Dimension of tensor network varieties
• The YODO algorithm: an efficient computational framework for sensitivity analysis in Bayesian networks
• Low-Rank Tensor Approximations for Solving Multimarginal Optimal Transport Problems
• High-dimensional density estimation with tensorizing flow
• Computing statistical moments via tensorization of polynomial chaos expansions
• Quasi-orthogonalization for alternating non-negative tensor factorization
• Gauging tensor networks with belief propagation
• A real generalized trisecant trichotomy
• Nonequilibrium steady-state dynamics of Markov processes on graphs

This page was built for publication: Duality of graphical models and tensor networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5006492)