pith. machine review for the scientific record. sign in

arxiv: 2604.14287 · v1 · submitted 2026-04-15 · 💻 cs.LG · cs.AI· quant-ph

Recognition: unknown

Quantum-inspired tensor networks in machine learning models

Alejandro Pozas-Kerstjens, Giannicola Scarpa, Guillermo Valverde, Igor Garc\'ia-Olaizola

Authors on Pith no claims yet

Pith reviewed 2026-05-10 13:46 UTC · model grok-4.3

classification 💻 cs.LG cs.AIquant-ph
keywords tensor networksmachine learningquantum many-body physicscomputational efficiencyexplainabilityprivacyneural network decomposition
0
0 comments X

The pith

Tensor networks from quantum many-body physics can serve as efficient alternative architectures or decompositions within machine learning models.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This review examines how tensor networks, developed to represent complex quantum states without exponential cost, are now being adapted for classical machine learning. The core idea rests on the observation that quantum entanglement patterns resemble the statistical correlations found in real-world data sets. The authors survey current uses of these networks as standalone models or as building blocks inside neural networks, then weigh reported gains in speed, interpretability, and data privacy against the practical obstacles that remain.

Core claim

Tensor networks mitigate the exponential complexity of many-body systems by capturing only the most relevant dependencies among particles; because quantum entanglement and classical statistical correlations share a formal similarity, the same compressed representations can be inserted into machine learning pipelines either as new learning architectures or as structured decompositions of neural-network layers, with the expectation of concrete advantages in computational efficiency, explainability, or privacy.

What carries the argument

Tensor networks as compressed representations of multiparticle quantum states that retain only the strongest dependencies among variables.

Load-bearing premise

The formal similarity between quantum entanglement and statistical correlations in ordinary data will produce measurable practical advantages once tensor networks are placed inside real machine-learning pipelines.

What would settle it

A side-by-side benchmark on standard image or text data sets in which tensor-network models show no reduction in training time, parameter count, or improvement in interpretability compared with ordinary neural networks of similar accuracy would falsify the expected advantages.

Figures

Figures reproduced from arXiv: 2604.14287 by Alejandro Pozas-Kerstjens, Giannicola Scarpa, Guillermo Valverde, Igor Garc\'ia-Olaizola.

Figure 1
Figure 1. Figure 1: Penrose notation for a scalar, vector, matrix, and a order-3 tensor. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Tensor network example. The matrices B and C, the order-3 tensor D, and the order-5 tensor A are multiplied along the relevant dimensions (i.e., contracted) to produce the order-4 tensor T. follow Einstein’s notation (Einstein, 1916) adding over repeated indices. 2.2 Tensor operations The first operation to consider is tensor reshaping, which consists of reorganizing the indices of a tensor without alterin… view at source ↗
Figure 3
Figure 3. Figure 3: Fundamental tensor network operations: (a) reshaping, (b) tensor contraction, (c) SVD de [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Gauge freedom and canonical forms: (a) inserting [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: A matrix product state of five sites. It is possible to give an MPS/TT representation of any tensor via a sequence of reshapings and singular value decompositions (see Fig. 3d). When cutting the singular values obtained this way to only χ of them, the ℓ2 error incurred corresponds to the sum of the singular values that have been left out (Verstraete and Cirac, 2006). Thus, the fidelity of a low-rank approx… view at source ↗
Figure 6
Figure 6. Figure 6: A matrix product operator of five sites. [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: PEPS lattice of size three. Unlike MPS, however, the exact contraction of general PEPS is computationally demanding (Schuch et al., 2007; Haferkamp et al., 2020; Scarpa et al., 2020), and their practical application, therefore, relies on approximate contraction schemes or renormalization-inspired methods (Cirac et al., 2021). In the context of machine learning, PEPS have been explored as supervised models … view at source ↗
Figure 8
Figure 8. Figure 8: Tree tensor network with eight leaf nodes. [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: MERA network. In contrast to TTNs, the disentanglers (blue rectangles) break short-range [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Graphical representations of common tensor decompositions. [PITH_FULL_IMAGE:figures/full_fig_p010_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Topic-author graph for the works analyzed. Green nodes correspond to topics, while pink [PITH_FULL_IMAGE:figures/full_fig_p028_11.png] view at source ↗
read the original abstract

Tensor networks were developed in the context of many-body physics as compressed representations of multiparticle quantum states. These representations mitigate the exponential complexity of many-body systems by capturing only the most relevant dependencies. Due to the formal similarity between quantum entanglement and statistical correlations, tensor networks have recently been integrated in machine learning, operating both as alternative learning architectures and as decompositions of components of neural networks. The expectation is that the theoretical understanding of tensor networks developed within quantum many-body physics leads to novel methods that offer advantages in terms of computational efficiency, explainability, or privacy. Here we review the use of tensor networks in the context of machine learning, providing a critical assessment of the state of the art, the potential advantages, and the challenges that must be overcome.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript reviews the application of tensor networks (developed in quantum many-body physics for compressing entangled states) to machine learning. It highlights the formal analogy between quantum entanglement and statistical correlations in classical data, surveys their use both as standalone ML architectures (e.g., MPS, TT, MERA) and as decompositions within neural networks, and provides a critical assessment of claimed advantages in computational efficiency, explainability, and privacy along with associated challenges.

Significance. If the critical assessment is balanced and identifies concrete conditions under which the quantum-inspired structures yield measurable gains, the review could help consolidate the subfield and reduce over-reliance on untested analogies. The explicit discussion of challenges is a strength, as is the synthesis of works across physics and ML; however, without new quantitative comparisons, its primary value lies in organizing existing literature rather than advancing novel claims.

major comments (1)
  1. [Abstract] Abstract: The central expectation that 'the theoretical understanding of tensor networks developed within quantum many-body physics leads to novel methods that offer advantages' rests on the entanglement-correlation analogy, yet the review does not appear to supply or reference explicit counter-examples or scaling analyses showing when this analogy fails (e.g., on dense random or high-dimensional tabular data lacking compressible low-rank structure). This weakens the critical assessment of potential advantages.
minor comments (2)
  1. The manuscript would benefit from a clearer taxonomy or table early on that maps specific tensor network types (MPS, TT, MERA, etc.) to the ML tasks where they have been applied, to improve readability for non-physicists.
  2. Some citations to foundational quantum TN papers could be added or updated to ensure the physics background section is fully self-contained.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive review and for identifying an opportunity to strengthen the critical assessment in the manuscript. We address the major comment below and will incorporate revisions to better highlight limitations of the entanglement-correlation analogy.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central expectation that 'the theoretical understanding of tensor networks developed within quantum many-body physics leads to novel methods that offer advantages' rests on the entanglement-correlation analogy, yet the review does not appear to supply or reference explicit counter-examples or scaling analyses showing when this analogy fails (e.g., on dense random or high-dimensional tabular data lacking compressible low-rank structure). This weakens the critical assessment of potential advantages.

    Authors: We agree that explicitly referencing cases where the analogy fails would improve the balance of the critical assessment. Although the manuscript already discusses challenges and limitations of tensor networks in machine learning (including data regimes without low-rank compressible structure) in the dedicated challenges section, we acknowledge that the abstract and introductory framing could more directly cite counter-examples. In the revised version, we will update the abstract to note that advantages are conditional on data structure and add references to relevant studies that provide scaling analyses or empirical demonstrations of underperformance on dense random data and high-dimensional tabular datasets lacking exploitable correlations. These additions draw from existing literature on tensor network limitations rather than new experiments, consistent with the review nature of the paper. revision: yes

Circularity Check

0 steps flagged

Review paper advances no derivations or quantitative predictions

full rationale

This is a survey paper that reviews existing applications of tensor networks to machine learning without presenting original derivations, new equations, fitted parameters, or quantitative predictions. The central claim is an expectation based on formal analogy between quantum entanglement and classical correlations, but no load-bearing step reduces by construction to its own inputs, self-citations, or fitted data. No equations or uniqueness theorems are invoked that could create circularity. The paper explicitly positions itself as providing a critical assessment of the state of the art rather than a self-contained theoretical derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a review paper; no new free parameters, axioms, or invented entities are introduced by the authors.

pith-pipeline@v0.9.0 · 5436 in / 945 out tokens · 38865 ms · 2026-05-10T13:46:59.252501+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

152 extracted references · 144 canonical work pages · 4 internal anchors

  1. [1]

    apsrmp4-2.bst 2018-12-27 (MD) hand-edited version of apsrmp4-1.bst

    FUNCTION id.bst "apsrmp4-2.bst 2018-12-27 (MD) hand-edited version of apsrmp4-1.bst" ENTRY address archive archivePrefix author bookaddress booktitle chapter collaboration doi edition editor eid eprint howpublished institution isbn issn journal key language month note number organization pages primaryClass publisher school SLACcitation series title transl...

    2018

  2. [2]

    and Li, Jerry and Liu, Allen and Narayanan, Shyam , booktitle =

    author author Acuaviva , A. , author V. Makam , author H. Nieuwboer , author D. Pérez-García , author F. Sittner , author M. Walter , and\ author F. Witteveen ( year 2023 ),\ title The minimal canonical form of a tensor network , \ in\ https://doi.org/10.1109/FOCS57990.2023.00027 booktitle 2023 IEEE 64th Annual Symposium on Foundations of Computer Science...

    work page doi:10.1109/focs57990.2023.00027 2023

  3. [3]

    , author S

    author author Aizpur\'ua , B. , author S. Palmer , and\ author R. Orús ( year 2025 ),\ title Tensor networks for explainable machine learning in cybersecurity , \ https://doi.org/10.1016/j.neucom.2025.130211 journal journal Neurocomputing \ volume 639 ,\ pages 130211 ,\ https://arxiv.org/abs/2401.00867 arXiv:2401.00867 ,\ DOI: https://doi.org/10.1016/j.ne...

    work page doi:10.1016/j.neucom.2025.130211 2025

  4. [4]

    , and\ author I

    author author Alkabetz , R. , and\ author I. Arad ( year 2021 ),\ title Tensor networks contraction and the belief propagation algorithm , \ https://doi.org/10.1103/PhysRevResearch.3.023073 journal journal Physical Review Research \ volume 3 ( number 2 ),\ pages 023073 ,\ https://arxiv.org/abs/2008.04433 arXiv:2008.04433 ,\ DOI: https://doi.org/10.1103/Ph...

    work page doi:10.1103/physrevresearch.3.023073 2021

  5. [5]

    In: Proceedings of 60 the 29th ACM International Conference on Architectural Support for Program- ming Languages and Operating Systems, Volume 2

    author author Ansel , J. , author E. Yang , author H. He , author N. Gimelshein , author A. Jain , author M. Voznesensky , author B. Bao , author P. Bell , author D. Berard , author E. Burovski , author G. Chauhan , author A. Chourdia , author W. Constable , author A. Desmaison , author Z. DeVito , author E. Ellison , author W. Feng , author J. Gong , aut...

    work page doi:10.1145/3620665.3640366 2024

  6. [6]

    , and\ author Z

    author author Arad , I. , and\ author Z. Landau ( year 2010 ),\ title Quantum computation and the evaluation of tensor networks , \ https://doi.org/10.1137/080739379 journal journal SIAM Journal on Computing \ volume 39 ( number 7 ),\ pages 3089 ,\ https://arxiv.org/abs/0805.0040 arXiv:0805.0040 ,\ DOI: https://doi.org/10.1137/080739379 10.1137/080739379 NoStop

    work page doi:10.1137/080739379 2010

  7. [7]

    , and\ author Q

    author author Barthel , T. , and\ author Q. Miao ( year 2025 ),\ title Absence of barren plateaus and scaling of gradients in the energy optimization of isometric tensor network states , \ https://doi.org/10.1007/s00220-024-05217-x journal journal Communications in Mathematical Physics \ volume 406 ( number 4 ),\ pages 86 ,\ DOI: https://doi.org/10.1007/s...

    work page doi:10.1007/s00220-024-05217-x 2025

  8. [8]

    Begušić, J

    author author Begušić , T. , author J. Gray , and\ author G. K.-L. \ Chan ( year 2024 ),\ title Fast and converged classical simulations of evidence for the utility of quantum computing before fault tolerance , \ https://doi.org/10.1126/sciadv.adk4321 journal journal Science Advances \ volume 10 ( number 3 ),\ pages eadk4321 ,\ https://arxiv.org/abs/2308....

    work page doi:10.1126/sciadv.adk4321 2024

  9. [9]

    PennyLane: Automatic differentiation of hybrid quantum-classical computations

    author author Bergholm , V. , author J. Izaac , author M. Schuld , author C. Gogolin , author S. Ahmed , author V. Ajith , author M. S. \ Alam , author G. Alonso-Linaje , author B. AkashNarayanan , author A. Asadi , author J. M. \ Arrazola , author U. Azad , author S. Banning , author C. Blank , author T. R. \ Bromley , author B. A. \ Cordier , author J. ...

    work page internal anchor Pith review arXiv 2018

  10. [10]

    Tensor networks in a nutshell,

    author author Biamonte , J. , and\ author V. Bergholm ( year 2017 ),\ @noop title Tensor networks in a nutshell , \ https://arxiv.org/abs/1708.00006 arXiv:1708.00006 NoStop

    work page arXiv 2017

  11. [11]

    author author Bridgeman , J. C. , and\ author C. T. \ Chubb ( year 2017 ),\ title Hand-waving and interpretive dance: an introductory course on tensor networks , \ https://doi.org/10.1088/1751-8121/aa6dc3 journal journal Journal of Physics A: Mathematical and Theoretical \ volume 50 ( number 22 ),\ pages 223001 ,\ https://arxiv.org/abs/1603.03039 arXiv:16...

    work page doi:10.1088/1751-8121/aa6dc3 2017

  12. [12]

    Extracting training data from diffusion models

    author author Carlini , N. , author J. Hayes , author M. Nasr , author M. Jagielski , author V. Sehwag , author F. Tramer , author B. Balle , author D. Ippolito , and\ author E. Wallace ( year 2023 ),\ title Extracting training data from diffusion models , \ in\ https://www.usenix.org/conference/usenixsecurity23/presentation/carlini booktitle Proceedings ...

    work page arXiv 2023

  13. [13]

    author author Carroll , J. D. , and\ author J.-J. \ Chang ( year 1970 ),\ title Analysis of individual differences in multidimensional scaling via an n -way generalization of `` Eckart-Young '' decomposition , \ https://doi.org/10.1007/BF02310791 journal journal Psychometrika \ volume 35 ( number 3 ),\ pages 283 ,\ DOI: https://doi.org/10.1007/BF02310791 ...

    work page doi:10.1007/bf02310791 1970

  14. [14]

    , author G

    author author Causer , L. , author G. M. \ Rotskoff , and\ author J. P. \ Garrahan ( year 2025 ),\ title Discrete generative diffusion models without stochastic differential equations: A tensor network approach , \ https://doi.org/10.1103/PhysRevE.111.025302 journal journal Physical Review E \ volume 111 ( number 2 ),\ pages 025302 ,\ https://arxiv.org/ab...

    work page doi:10.1103/physreve.111.025302 2025

  15. [15]

    , and\ author T

    author author Chen , H. , and\ author T. Barthel ( year 2024 ),\ title Machine learning with tree tensor networks, CP rank constraints, and tensor dropout , \ https://doi.org/10.1109/tpami.2024.3396386 journal journal IEEE Transactions on Pattern Analysis and Machine Intelligence \ volume 46 ( number 12 ),\ pages 7825 ,\ https://arxiv.org/abs/2305.19440 a...

    work page doi:10.1109/tpami.2024.3396386 2024

  16. [16]

    author author Chen , S. Y.-C. , author C.-M. \ Huang , author C.-W. \ Hsing , and\ author Y.-J. \ Kao ( year 2021 ),\ title An end-to-end trainable hybrid classical-quantum classifier , \ https://doi.org/10.1088/2632-2153/ac104d journal journal Machine Learning: Science and Technology \ volume 2 ( number 4 ),\ pages 045021 ,\ https://arxiv.org/abs/2102.02...

    work page doi:10.1088/2632-2153/ac104d 2021

  17. [17]

    , author K

    author author Chen , Z. , author K. Batselier , author J. A. K. \ Suykens , and\ author N. Wong ( year 2017 ),\ title Parallelized tensor train learning of polynomial classifiers , \ https://doi.org/10.1109/tnnls.2017.2771264 journal journal IEEE Transactions on Neural Networks and Learning Systems \ volume 29 ( number 10 ),\ pages 4621 ,\ https://arxiv.o...

    work page doi:10.1109/tnnls.2017.2771264 2017

  18. [18]

    , author L

    author author Cheng , S. , author L. Wang , author T. Xiang , and\ author P. Zhang ( year 2019 ),\ title Tree tensor networks for generative modeling , \ https://doi.org/10.1103/physrevb.99.155131 journal journal Physical Review B \ volume 99 ( number 15 ),\ pages 155131 ,\ https://arxiv.org/abs/1901.02217 arXiv:1901.02217 ,\ DOI: https://doi.org/10.1103/...

    work page doi:10.1103/physrevb.99.155131 2019

  19. [19]

    , author L

    author author Cheng , S. , author L. Wang , and\ author P. Zhang ( year 2021 ),\ title Supervised learning with projected entangled pair states , \ https://doi.org/10.1103/physrevb.103.125117 journal journal Physical Review B \ volume 103 ( number 12 ),\ pages 125117 ,\ https://arxiv.org/abs/2009.09932 arXiv:2009.09932 ,\ DOI: https://doi.org/10.1103/phys...

    work page doi:10.1103/physrevb.103.125117 2021

  20. [20]

    Vggsound: A Large-Scale Audio-Visual Dataset

    author author Cheng , Z. , author B. Li , author Y. Fan , and\ author Y. Bao ( year 2020 ),\ title A novel rank selection scheme in tensor ring decomposition based on reinforcement learning for deep neural networks , \ in\ https://doi.org/10.1109/icassp40776.2020.9053292 booktitle ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and S...

    work page doi:10.1109/icassp40776.2020.9053292 2020

  21. [21]

    , author P

    author author Chi-Chung , L. , author P. Sadayappan , and\ author R. Wenger ( year 1997 ),\ title On optimizing a class of multi-dimensional loops with reduction for parallel execution , \ https://doi.org/10.1142/S0129626497000176 journal journal Parallel Processing Letters \ volume 07 ( number 02 ),\ pages 157 ,\ DOI: https://doi.org/10.1142/S01296264970...

    work page doi:10.1142/s0129626497000176 1997

  22. [22]

    , author N

    author author Cichocki , A. , author N. Lee , author I. Oseledets , author A. H. \ Phan , author Q. Zhao , and\ author D. P. \ Mandic ( year 2016 ),\ title Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions , \ https://doi.org/10.1561/2200000059 journal journal Foundations and Trends in Machine...

    work page doi:10.1561/2200000059 2016

  23. [23]

    , author N

    author author Cichocki , A. , author N. Lee , author I. Oseledets , author A. H. \ Phan , author Q. Zhao , author M. Sugiyama , and\ author D. P. \ Mandic ( year 2017 ),\ title Tensor networks for dimensionality reduction and large-scale optimization: Part 2 applications and future perspectives , \ https://doi.org/10.1561/2200000067 journal journal Founda...

    work page doi:10.1561/2200000067 2017

  24. [24]

    author author Cirac , J. I. , author D. P\'erez-Garc\' a , author N. Schuch , and\ author F. Verstraete ( year 2021 ),\ title Matrix product states and projected entangled pair states: Concepts, symmetries, theorems , \ https://doi.org/10.1103/RevModPhys.93.045003 journal journal Reviews of Modern Physics \ volume 93 ,\ pages 045003 ,\ https://arxiv.org/a...

    work page doi:10.1103/revmodphys.93.045003 2021

  25. [25]

    , author F

    author author Dborin , J. , author F. Barratt , author V. Wimalaweera , author L. Wright , and\ author A. G. \ Green ( year 2022 ),\ title Matrix product state pre-training for quantum machine learning , \ https://doi.org/10.1088/2058-9565/ac7073 journal journal Quantum Science and Technology \ volume 7 ( number 3 ),\ pages 035014 ,\ https://arxiv.org/abs...

    work page doi:10.1088/2058-9565/ac7073 2022

  26. [26]

    author author Dwork , C. ( year 2006 ),\ title Differential privacy , \ in\ https://doi.org/10.1007/11787006\_1 booktitle Automata, Languages and Programming ,\ series Lecture Notes in Computer Science , Vol.\ volume 4052 ,\ editor edited by\ editor M. Bugliesi , editor B. Preneel , editor V. Sassone , \ and\ editor I. Wegener \ ( publisher Springer Berli...

    work page doi:10.1007/11787006 2006

  27. [27]

    URLhttps://doi.org/10.1561/ 0400000042

    author author Dwork , C. , and\ author A. Roth ( year 2014 ),\ title The algorithmic foundations of differential privacy , \ https://doi.org/10.1561/0400000042 journal journal Foundations and Trends in Theoretical Computer Science \ volume 9 ( number 3–4 ),\ pages 211 ,\ DOI: https://doi.org/10.1561/0400000042 10.1561/0400000042 ,\ note https://www.cis.up...

    work page doi:10.1561/0400000042 2014

  28. [28]

    1936 , month = sep, publisher =

    author author Eckart , C. , and\ author G. Young ( year 1936 ),\ title The approximation of one matrix by another of lower rank , \ https://doi.org/10.1007/BF02288367 journal journal Psychometrika \ volume 1 ( number 3 ),\ pages 211 ,\ DOI: https://doi.org/10.1007/BF02288367 10.1007/BF02288367 NoStop

    work page doi:10.1007/bf02288367 1936

  29. [29]

    author author Einstein , A. ( year 1916 ),\ title Die grundlage der allgemeinen relativitätstheorie , \ https://doi.org/https://doi.org/10.1002/andp.19163540702 journal journal Annalen der Physik \ volume 354 ( number 7 ),\ pages 769 ,\ https://arxiv.org/abs/https://web.archive.org/web/20060829045130/http://www.alberteinstein.info/gallery/gtext3.html http...

    work page doi:10.1002/andp.19163540702 1916

  30. [30]

    Fannes , author B

    author author Fannes , M. , author B. Nachtergaele , and\ author R. F. \ Werner ( year 1992 ),\ title Finitely correlated states on quantum spin chains , \ https://doi.org/10.1007/BF02099178 journal journal Communications in Mathematical Physics \ volume 144 ,\ pages 443 ,\ DOI: https://doi.org/10.1007/BF02099178 10.1007/BF02099178 NoStop

    work page doi:10.1007/bf02099178 1992

  31. [31]

    , author M

    author author Felser , T. , author M. Trenti , author L. Sestini , author A. Gianelle , author D. Zuliani , author D. Lucchesi , and\ author S. Montangero ( year 2021 ),\ title Quantum-inspired machine learning on high-energy physics data , \ https://doi.org/10.1038/s41534-021-00443-w journal journal npj Quantum Information \ volume 7 ,\ pages 111 ,\ http...

    work page doi:10.1038/s41534-021-00443-w 2021

  32. [32]

    Fishman, S

    author author Fishman , M. , author S. White , and\ author E. M. \ Stoudenmire ( year 2022 ),\ title The ITensor software library for tensor network calculations , \ https://doi.org/10.21468/SciPostPhysCodeb.4 journal journal SciPost Physics Codebases \ volume \!\!\! ,\ pages 4 ,\ https://arxiv.org/abs/2007.14822 arXiv:2007.14822 ,\ DOI: https://doi.org/1...

    work page doi:10.21468/scipostphyscodeb.4 2022

  33. [33]

    , author S

    author author Gao , Z.-F. , author S. Cheng , author R.-Q. \ He , author Z. Y. \ Xie , author H. Zhao , author Z.-Y. \ Lu , and\ author T. Xiang ( year 2020 ),\ title Compressing deep neural networks by matrix product operators , \ https://doi.org/10.1103/physrevresearch.2.023300 journal journal Physical Review Research \ volume 2 ,\ pages 023300 ,\ https...

    work page doi:10.1103/physrevresearch.2.023300 2020

  34. [34]

    , author N

    author author Glasser , I. , author N. Pancotti , and\ author J. I. \ Cirac ( year 2020 ),\ title From probabilistic graphical models to generalized tensor networks for supervised learning , \ https://doi.org/10.1109/ACCESS.2020.2986279 journal journal IEEE Access \ volume 8 ,\ pages 68169 ,\ https://arxiv.org/abs/1806.05964 arXiv:1806.05964 ,\ DOI: https...

    work page doi:10.1109/access.2020.2986279 2020

  35. [35]

    , author R

    author author Glasser , I. , author R. Sweke , author N. Pancotti , author J. Eisert , and\ author I. Cirac ( year 2019 ),\ title Expressive power of tensor-network factorizations for probabilistic modeling , \ https://dl.acm.org/doi/10.5555/3454287.3454421 journal journal Advances in Neural Information Processing Systems \ volume 32 ,\ https://arxiv.org/...

    work page doi:10.5555/3454287.3454421 2019

  36. [36]

    author author Grasedyck , L. ( year 2010 ),\ title Hierarchical singular value decomposition of tensors , \ https://doi.org/10.1137/090764189 journal journal SIAM Journal on Matrix Analysis and Applications \ volume 31 ( number 4 ),\ pages 2029 ,\ DOI: https://doi.org/10.1137/090764189 10.1137/090764189 NoStop

    work page doi:10.1137/090764189 2010

  37. [37]

    author author Gray , J. ( year 2018 ),\ title quimb: A Python package for quantum information and many-body calculations , \ https://doi.org/10.21105/joss.00819 journal journal Journal of Open Source Software \ volume 3 ( number 29 ),\ pages 819 ,\ DOI: https://doi.org/10.21105/joss.00819 10.21105/joss.00819 ,\ note https://quimb.readthedocs.io NoStop

    work page doi:10.21105/joss.00819 2018

  38. [38]

    , author S

    author author Guala , D. , author S. Zhang , author E. Cruz , author C. Riofrio , author J. Klepsch , and\ author J. M. \ Arrazola ( year 2023 ),\ title Practical overview of image classification with tensor-network quantum circuits , \ https://doi.org/10.1038/s41598-023-30258-y journal journal Scientific Reports \ volume 13 ,\ pages 4427 ,\ https://arxiv...

    work page doi:10.1038/s41598-023-30258-y 2023

  39. [39]

    author author Hackbusch , W. ( year 2012 ),\ https://doi.org/10.1007/978-3-642-28027-6_11 title Tensor Spaces and Numerical Tensor Calculus \ ( publisher Springer Berlin Heidelberg ,\ address Berlin, Heidelberg ) NoStop

    work page doi:10.1007/978-3-642-28027-6_11 2012

  40. [40]

    , and\ author S

    author author Hackbusch , W. , and\ author S. K \"u hn ( year 2009 ),\ title A new scheme for the tensor representation , \ https://doi.org/10.1007/s00041-009-9094-9 journal journal Journal of Fourier analysis and applications \ volume 15 ( number 5 ),\ pages 706 ,\ DOI: https://doi.org/10.1007/s00041-009-9094-9 10.1007/s00041-009-9094-9 NoStop

    work page doi:10.1007/s00041-009-9094-9 2009

  41. [41]

    Contracting projected entangled pair states is average-case hard.Phys

    author author Haferkamp , J. , author D. Hangleiter , author J. Eisert , and\ author M. Gluza ( year 2020 ),\ title Contracting projected entangled pair states is average-case hard , \ https://doi.org/10.1103/PhysRevResearch.2.013010 journal journal Physical Review Research \ volume 2 ,\ pages 013010 ,\ https://arxiv.org/abs/1810.00738 arXiv:1810.00738 ,\...

    work page doi:10.1103/physrevresearch.2.013010 2020

  42. [42]

    , author K

    author author Haliassos , A. , author K. Konstantinidis , and\ author D. P. \ Mandic ( year 2021 ),\ title Supervised learning for nonsequential data: A canonical polyadic decomposition approach , \ https://doi.org/10.1109/tnnls.2021.3069399 journal journal IEEE Transactions on Neural Networks and Learning Systems \ volume 33 ( number 10 ),\ pages 5162 ,\...

    work page doi:10.1109/tnnls.2021.3069399 2021

  43. [43]

    , author J

    author author Han , Z.-Y. , author J. Wang , author H. Fan , author L. Wang , and\ author P. Zhang ( year 2018 ),\ title Unsupervised generative modeling using Matrix Product States , \ https://doi.org/10.1103/PhysRevX.8.031012 journal journal Physical Review X \ volume 8 ,\ pages 031012 ,\ https://arxiv.org/abs/1709.01662 arXiv:1709.01662 ,\ DOI: https:/...

    work page doi:10.1103/physrevx.8.031012 2018

  44. [44]

    author author Harris , C. R. , author K. J. \ Millman , author S. J. \ van der Walt , author R. Gommers , author P. Virtanen , author D. Cournapeau , author E. Wieser , author J. Taylor , author S. Berg , author N. J. \ Smith , author R. Kern , author M. Picus , author S. Hoyer , author M. H. \ van Kerkwijk , author M. Brett , author A. Haldane , author J...

    work page doi:10.1038/s41586-020-2649-2 2020

  45. [45]

    Hauschild and F

    author author Hauschild , J. , and\ author F. Pollmann ( year 2018 ),\ title Efficient numerical simulations with Tensor Networks: Tensor Network Python (TeNPy) , \ https://doi.org/10.21468/SciPostPhysLectNotes.5 journal journal SciPost Physics Lecture Notes \ volume \!\!\! ,\ pages 5 ,\ https://arxiv.org/abs/1805.00055 arXiv:1805.00055 ,\ DOI: https://do...

    work page doi:10.21468/scipostphyslectnotes.5 2018

  46. [46]

    , author J

    author author Hou , Y. , author J. Li , author T. Xu , and\ author X. Liu ( year 2024 ),\ title A hybrid quantum-classical classification model based on branching multi-scale entanglement renormalization ansatz , \ https://doi.org/10.1038/s41598-024-69384-6 journal journal Scientific Reports \ volume 14 ,\ pages 18521 ,\ https://arxiv.org/abs/2303.07906 a...

    work page doi:10.1038/s41598-024-69384-6 2024

  47. [47]

    , author V

    author author Hrinchuk , O. , author V. Khrulkov , author L. Mirvakhabova , author E. Orlova , and\ author I. Oseledets ( year 2020 ),\ title Tensorized embedding layers , \ in\ https://doi.org/10.18653/v1/2020.findings-emnlp.436 booktitle Findings of the Association for Computational Linguistics: EMNLP 2020 ,\ https://arxiv.org/abs/1901.10787 arXiv:1901....

    work page doi:10.18653/v1/2020.findings-emnlp.436 2020

  48. [48]

    author author Hu , E. J. , author Y. Shen , author P. Wallis , author Z. Allen-Zhu , author Y. Li , author S. Wang , author L. Wang , author W. Chen , et al. ( year 2022 ),\ title Lora: Low-rank adaptation of large language models. \ @noop journal journal Iclr \ volume 1 ( number 2 ),\ pages 3 ,\ https://arxiv.org/abs/2106.09685 arXiv:2106.09685 NoStop

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  49. [49]

    Towards quantum machine learning with tensor networks

    author author Huggins , W. , author P. Patil , author B. Mitchell , author K. B. \ Whaley , and\ author E. M. \ Stoudenmire ( year 2019 ),\ title Towards quantum machine learning with tensor networks , \ https://doi.org/10.1088/2058-9565/aaea94 journal journal Quantum Science and Technology \ volume 4 ( number 2 ),\ pages 024001 ,\ https://arxiv.org/abs/1...

    work page doi:10.1088/2058-9565/aaea94 2019

  50. [50]

    Quantum computing with Qiskit

    author author Javadi-Abhari , A. , author M. Treinish , author K. Krsulich , author C. J. \ Wood , author J. Lishman , author J. Gacon , author S. Martiel , author P. D. \ Nation , author L. S. \ Bishop , author A. W. \ Cross , author B. R. \ Johnson , and\ author J. M. \ Gambetta ( year 2024 ),\ @noop title Quantum computing with Qiskit , \ https://arxiv...

    work page internal anchor Pith review arXiv 2024

  51. [51]

    , author Q

    author author Ji , Y. , author Q. Wang , author X. Li , and\ author J. Liu ( year 2019 ),\ title A survey on tensor techniques and applications in machine learning , \ https://doi.org/10.1109/ACCESS.2019.2949814 journal journal IEEE Access \ volume 7 ,\ pages 162950 ,\ DOI: https://doi.org/10.1109/ACCESS.2019.2949814 10.1109/ACCESS.2019.2949814 NoStop

    work page doi:10.1109/access.2019.2949814 2019

  52. [52]

    , author T

    author author Jin , R. , author T. G. \ Kolda , and\ author R. Ward ( year 2020 a ),\ title Faster Johnson--Lindenstrauss transforms via Kronecker products , \ https://doi.org/10.1093/imaiai/iaaa028 journal journal Information and Inference: A Journal of the IMA \ volume 10 ( number 4 ),\ pages 1533 ,\ https://arxiv.org/abs/1909.04801 arXiv:1909.04801 ,\ ...

    work page doi:10.1093/imaiai/iaaa028 2020

  53. [53]

    , author J

    author author Jin , X. , author J. Tang , author X. Kong , author Y. Peng , author J. Cao , author Q. Zhao , and\ author W. Kong ( year 2020 b ),\ title CTNN : A convolutional tensor-train neural network for multi-task brainprint recognition , \ https://doi.org/10.1109/tnsre.2020.3035786 journal journal IEEE Transactions on Neural Systems and Rehabilitati...

    work page doi:10.1109/tnsre.2020.3035786 2020

  54. [54]

    On the simulation of quantum circuits

    author author Jozsa , R. ( year 2006 ),\ @noop title On the simulation of quantum circuits , \ https://arxiv.org/abs/quant-ph/0603163 arXiv:quant-ph/0603163 NoStop

    work page arXiv 2006

  55. [55]

    author author Kilmer , M. E. , author L. Horesh , author H. Avron , and\ author E. Newman ( year 2021 ),\ title Tensor-tensor algebra for optimal representation and compression of multiway data , \ https://doi.org/10.1073/pnas.2015851118 journal journal Proceedings of the National Academy of Sciences \ volume 118 ( number 28 ),\ pages e2015851118 ,\ https...

    work page doi:10.1073/pnas.2015851118 2021

  56. [56]

    author author Kiwit , F. J. , author B. Jobst , author A. Luckow , author F. Pollmann , and\ author C. A. \ Riofr\'o ( year 2025 ),\ title Typical machine learning datasets as low-depth quantum circuits , \ https://doi.org/10.1088/2058-9565/ae0123 journal journal Quantum Science and Technology \ volume 10 ( number 4 ),\ pages 045035 ,\ https://arxiv.org/a...

    work page doi:10.1088/2058-9565/ae0123 2025

  57. [57]

    , author X.-Y

    author author Kong , F. , author X.-Y. \ Liu , and\ author R. Henao ( year 2021 ),\ @noop title Quantum tensor network in machine learning: An application to tiny object classification , \ https://arxiv.org/abs/2101.03154 arXiv:2101.03154 NoStop

    work page arXiv 2021

  58. [58]

    , author Y

    author author Kossaifi , J. , author Y. Panagakis , author A. Anandkumar , and\ author M. Pantic ( year 2019 ),\ title Tensor L y: Tensor learning in P ython , \ @noop journal journal Journal of Machine Learning Research \ volume 20 ( number 26 ),\ pages 1 ,\ https://arxiv.org/abs/1610.09555 arXiv:1610.09555 ,\ note https://tensorly.org NoStop

    work page arXiv 2019

  59. [59]

    , author B

    author author Kressner , D. , author B. Vandereycken , and\ author R. Voorhaar ( year 2023 ),\ title Streaming tensor train approximation , \ https://doi.org/10.1137/22m1515045 journal journal SIAM Journal on Scientific Computing \ volume 45 ( number 5 ),\ pages A2610 ,\ https://arxiv.org/abs/2208.02600 arXiv:2208.02600 ,\ DOI: https://doi.org/10.1137/22m...

    work page doi:10.1137/22m1515045 2023

  60. [60]

    , author I

    author author Krizhevsky , A. , author I. Sutskever , and\ author G. E. \ Hinton ( year 2012 ),\ title ImageNet classification with deep convolutional neural networks , \ in\ https://papers.nips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html booktitle Advances in Neural Information Processing Systems ,\ Vol. volume 25 ,\ edi...

    2012

  61. [61]

    author author Latorre , J. I. ( year 2005 ),\ @noop title Image compression and entanglement , \ https://arxiv.org/abs/quant-ph/0510031 arXiv:quant-ph/0510031 NoStop

    work page arXiv 2005

  62. [62]

    , author D

    author author Lee , D. , author D. Wang , author Y. Yang , author L. Deng , author G. Zhao , and\ author G. Li ( year 2021 ),\ title QTTnet : Quantized tensor train neural networks for 3D object and video recognition , \ https://doi.org/10.1016/j.neunet.2021.05.034 journal journal Neural Networks \ volume 141 ,\ pages 420 ,\ DOI: https://doi.org/10.1016/j...

    work page doi:10.1016/j.neunet.2021.05.034 2021

  63. [63]

    , author O

    author author Levine , Y. , author O. Sharir , author N. Cohen , and\ author A. Shashua ( year 2019 ),\ title Quantum entanglement in deep learning architectures , \ https://doi.org/10.1103/physrevlett.122.065301 journal journal Physical Review Letters \ volume 122 ( number 6 ),\ pages 065301 ,\ https://arxiv.org/abs/1803.09780 arXiv:1803.09780 ,\ DOI: ht...

    work page doi:10.1103/physrevlett.122.065301 2019

  64. [64]

    Pruning and quantization for deep neural network acceleration: A su r- vey,

    author author Liang , T. , author J. Glossner , author L. Wang , author S. Shi , and\ author X. Zhang ( year 2021 ),\ title Pruning and quantization for deep neural network acceleration: A survey , \ https://doi.org/10.1016/j.neucom.2021.07.045 journal journal Neurocomputing \ volume 461 ,\ pages 370 ,\ DOI: https://doi.org/10.1016/j.neucom.2021.07.045 10...

    work page doi:10.1016/j.neucom.2021.07.045 2021

  65. [65]

    , author I

    author author Liao , H. , author I. Convy , author Z. Yang , and\ author K. B. \ Whaley ( year 2023 a ),\ title Decohering tensor network quantum machine learning models , \ https://doi.org/10.1007/s42484-022-00095-9 journal journal Quantum Machine Intelligence \ volume 5 ,\ pages 7 ,\ https://arxiv.org/abs/2209.01195 arXiv:2209.01195 ,\ DOI: https://doi....

    work page doi:10.1007/s42484-022-00095-9 2023

  66. [66]

    Differentiable programming tensor networks.Physical Review X, 9(3):031041, 2019.doi:10.1103/physrevx.9.031041

    author author Liao , H.-J. , author J.-G. \ Liu , author L. Wang , and\ author T. Xiang ( year 2019 ),\ title Differentiable programming tensor networks , \ https://doi.org/10.1103/physrevx.9.031041 journal journal Physical Review X \ volume 9 ( number 3 ),\ pages 031041 ,\ https://arxiv.org/abs/1903.09650 arXiv:1903.09650 ,\ DOI: https://doi.org/10.1103/...

    work page doi:10.1103/physrevx.9.031041 2019

  67. [67]

    , author K

    author author Liao , H.-J. , author K. Wang , author Z.-S. \ Zhou , author P. Zhang , and\ author T. Xiang ( year 2023 b ),\ @noop title Simulation of IBM's kicked Ising experiment with Projected Entangled Pair Operator , \ https://arxiv.org/abs/2308.03082 arXiv:2308.03082 NoStop

    work page arXiv 2023

  68. [68]

    , author S.-J

    author author Liu , D. , author S.-J. \ Ran , author P. Wittek , author P. Cheng , author R. B. \ García , author G. Su , and\ author M. Lewenstein ( year 2019 ),\ title Machine learning by unitary tensor network of hierarchical tree structure , \ https://doi.org/10.1088/1367-2630/ab31ef journal journal New Journal of Physics \ volume 21 ( number 7 ),\ pa...

    work page doi:10.1088/1367-2630/ab31ef 2019

  69. [69]

    , author L

    author author Liu , H. , author L. T. \ Yang , author Y. Guo , author X. Xie , and\ author J. Ma ( year 2018 ),\ title An incremental tensor-train decomposition for cyber-physical-social big data , \ https://doi.org/10.1109/tbdata.2018.2867485 journal journal IEEE Transactions on Big Data \ volume 7 ( number 2 ),\ pages 341 ,\ DOI: https://doi.org/10.1109...

    work page doi:10.1109/tbdata.2018.2867485 2018

  70. [70]

    , author S

    author author Liu , J. , author S. Li , author J. Zhang , and\ author P. Zhang ( year 2023 ),\ title Tensor networks for unsupervised machine learning , \ https://doi.org/10.1103/physreve.107.l012103 journal journal Physical Review E \ volume 107 ,\ pages L012103 ,\ https://arxiv.org/abs/2106.12974 arXiv:2106.12974 ,\ DOI: https://doi.org/10.1103/physreve...

    work page doi:10.1103/physreve.107.l012103 2023

  71. [71]

    , author J

    author author Liu , Y. , author J. Liu , and\ author C. Zhu ( year 2020 ),\ title Low-rank tensor train coefficient array estimation for tensor-on-tensor regression , \ https://doi.org/10.1109/tnnls.2020.2967022 journal journal IEEE Transactions on Neural Networks and Learning Systems \ volume 31 ( number 12 ),\ pages 5402 ,\ DOI: https://doi.org/10.1109/...

    work page doi:10.1109/tnnls.2020.2967022 2020

  72. [72]

    , author P

    author author Ma , X. , author P. Zhang , author S. Zhang , author N. Duan , author Y. Hou , author M. Zhou , and\ author D. Song ( year 2019 ),\ title A tensorized transformer for language modeling , \ in\ https://dl.acm.org/doi/10.5555/3454287.3454487 booktitle Advances in Neural Information Processing Systems ,\ Vol. volume 32 \ ( publisher Curran Asso...

    work page doi:10.5555/3454287.3454487 2019

  73. [73]

    , author S

    author author Marzouk , R. , author S. Bassan , and\ author G. Katz ( year 2025 ),\ @noop title SHAP meets tensor networks: Provably tractable explanations with parallelism , \ https://arxiv.org/abs/2510.21599 arXiv:2510.21599 NoStop

    work page arXiv 2025

  74. [74]

    , author J

    author author Meiburg , A. , author J. Chen , author J. Miller , author R. Tihon , author G. Rabusseau , and\ author A. Perdomo-Ortiz ( year 2025 ),\ title Generative learning of continuous data by tensor networks , \ https://doi.org/10.21468/SciPostPhys.18.3.096 journal journal SciPost Physics \ volume 18 ( number 3 ),\ pages 096 ,\ DOI: https://doi.org/...

    work page doi:10.21468/scipostphys.18.3.096 2025

  75. [75]

    , author B

    author author Mossi , A. , author B. Z unkovi c , and\ author K. Flouris ( year 2025 ),\ title A matrix product state model for simultaneous classification and generation , \ https://doi.org/10.1007/s42484-025-00272-6 journal journal Quantum Machine Intelligence \ volume 7 ( number 1 ),\ pages 48 ,\ DOI: https://doi.org/10.1007/s42484-025-00272-6 10.1007/...

    work page doi:10.1007/s42484-025-00272-6 2025

  76. [76]

    Distribution of entanglement in two-dimensional square grid network,

    author author Moussa , C. , author H. Wang , author M. Araya-Polo , author T. Bäck , and\ author V. Dunjko ( year 2023 ),\ title Application of quantum-inspired generative models to small molecular datasets , \ in\ https://doi.org/10.1109/qce57702.2023.00046 booktitle 2023 IEEE International Conference on Quantum Computing and Engineering (QCE) \ ( publis...

    work page doi:10.1109/qce57702.2023.00046 2023

  77. [77]

    author author Nielsen , M. A. , and\ author I. L. \ Chuang ( year 2010 ),\ @noop title Quantum Computation and Quantum Information ,\ edition 10th \ ed.\ ( publisher Cambridge University Press ,\ address Cambridge ) NoStop

    2010

  78. [78]

    , author D

    author author Novikov , A. , author D. Podoprikhin , author A. Osokin , and\ author D. P. \ Vetrov ( year 2015 ),\ title Tensorizing neural networks , \ https://dl.acm.org/doi/10.5555/2969239.2969289 journal journal Advances in Neural Information Processing Systems \ volume 28 ,\ https://arxiv.org/abs/1509.06569 arXiv:1509.06569 NoStop

    work page doi:10.5555/2969239.2969289 2015

  79. [79]

    , author M

    author author Novikov , A. , author M. Trofimov , and\ author I. Oseledets ( year 2018 ),\ title Exponential machines , \ https://doi.org/10.24425/bpas.2018.125926 journal journal Bulletin of the Polish Academy of Sciences. Technical Sciences \ volume 66 ( number 6 ),\ pages 789–797 ,\ https://arxiv.org/abs/1605.03795 arXiv:1605.03795 ,\ DOI: https://doi....

    work page doi:10.24425/bpas.2018.125926 2018

  80. [80]

    ),\ @noop title cuTensorNet library , \ note https://docs.nvidia.com/cuda/cuquantum/latest/cutensornet/index.html NoStop

    author author NVIDIA , ( year n.d. ),\ @noop title cuTensorNet library , \ note https://docs.nvidia.com/cuda/cuquantum/latest/cutensornet/index.html NoStop

Showing first 80 references.