{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:02:29Z","timestamp":1792785749976,"version":"4.5.0"},"reference-count":44,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T00:00:00Z","timestamp":1626220800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T00:00:00Z","timestamp":1626220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Science Foundation","award":["CCF-1525943"],"award-info":[{"award-number":["CCF-1525943"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We present an algorithm for supervised learning using tensor networks, employing a step of data pre-processing by coarse-graining through a sequence of wavelet transformations. These transformations are represented as a set of tensor network layers identical to those in a multi-scale entanglement renormalization ansatz tensor network. We perform supervised learning and regression tasks through a model based on a matrix product states (MPSs) acting on the coarse-grained data. Because the entire model consists of tensor contractions (apart from the initial non-linear feature map), we can adaptively fine-grain the optimized MPS model \u2018backwards\u2019 through the layers with essentially no loss in performance. The MPS itself is trained using an adaptive algorithm based on the density matrix renormalization group algorithm. We test our methods by performing a classification task on audio data and a regression task on temperature time-series data, studying the dependence of training accuracy on the number of coarse-graining layers and showing how fine-graining through the network may be used to initialize models which access finer-scale features.<\/jats:p>","DOI":"10.1088\/2632-2153\/abffe8","type":"journal-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T18:18:35Z","timestamp":1620757115000},"page":"035036","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Multi-scale tensor network architecture for machine learning"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6330-9801","authenticated-orcid":false,"given":"J A","family":"Reyes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E M","family":"Stoudenmire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,7,14]]},"reference":[{"key":"mlstabffe8bib1","article-title":"Machine learning assisted measurement of local topological invariants","author":"Marcello","year":"2019"},{"key":"mlstabffe8bib2","doi-asserted-by":"crossref","DOI":"10.1109\/ITW44776.2019.8989133","article-title":"Neural decoder for topological codes using pseudo-inverse of parity check matrix","author":"Chinni","year":"2019"},{"key":"mlstabffe8bib3","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1038\/s41567-019-0512-x","article-title":"Identifying topological order through unsupervised machine learning","volume":"15","author":"Rodriguez-Nieva","year":"2019","journal-title":"Nat. Phys."},{"key":"mlstabffe8bib4","article-title":"Optimizing quantum error correction codes with reinforcement learning","author":"Nautrup","year":"2018"},{"key":"mlstabffe8bib5","article-title":"Detecting quantum speedup by quantum walk with convolutional neural networks","author":"Melkinov","year":"2019"},{"key":"mlstabffe8bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2019.112790","article-title":"An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications","volume":"362","author":"Samaniego","year":"2020","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstabffe8bib7","article-title":"Tensorizing neural networks","author":"Novikov","year":"2015"},{"key":"mlstabffe8bib8","article-title":"Exponential machines","author":"Novikov","year":"2016"},{"key":"mlstabffe8bib9","first-page":"4799","article-title":"Supervised learning with quantum inspired tensor networks","volume":"29","author":"Stoudenmire","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"mlstabffe8bib10","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aaba1a","article-title":"Learning relevant features of data with multi-scale tensor networks","volume":"3","author":"Stoudenmire","year":"2018","journal-title":"Quant. Sci. Tech."},{"key":"mlstabffe8bib11","article-title":"Supervised learning with generalized tensor networks","author":"Glasser","year":"2018"},{"key":"mlstabffe8bib12","article-title":"Long term forecasting using tensor-train RNNs","author":"Yu","year":"2017"},{"key":"mlstabffe8bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031012","article-title":"Unsupervised generative modeling using matrix product states","volume":"8","author":"Han","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstabffe8bib14","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/ab31ef","article-title":"Machine learning by unitary tensor network of hierarchical tree structure","volume":"21","author":"Liu","year":"2019","journal-title":"New J. Phys."},{"key":"mlstabffe8bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.155131","article-title":"Tree tensor networks for generative modeling","volume":"99","author":"Cheng","year":"2019","journal-title":"Phys. Rev. B"},{"key":"mlstabffe8bib16","article-title":"Deep learning and quantum entanglement: fundamental connections with implications to network design","author":"Levine","year":"2017"},{"key":"mlstabffe8bib17","article-title":"Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learning","author":"Glasser","year":"2019"},{"key":"mlstabffe8bib18","article-title":"MERACLE: constructive layer-wise conversion of a tensor train into a MERA","author":"Batselier","year":"2019"},{"key":"mlstabffe8bib19","first-page":"1","article-title":"Tensor regression networks","volume":"21","author":"Kossaifi","year":"2020","journal-title":"JMLR"},{"key":"mlstabffe8bib20","article-title":"Modeling sequences with quantum states: a look under the hood","author":"Bradley","year":"2019"},{"key":"mlstabffe8bib21","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.aop.2014.06.013","article-title":"A practical introduction to tensor network states: matrix product states and projected entangled pair states","volume":"349","author":"Orus","year":"2014","journal-title":"Ann. Phys., NY"},{"key":"mlstabffe8bib22","article-title":"Tensor networks for big data analytics and large-scale optimization problems","author":"Cichocki","year":"2014"},{"key":"mlstabffe8bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.91.147902","article-title":"Efficient classical simulation of slightly entangled quantum computations","volume":"91","author":"Vidal","year":"2003","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib24","first-page":"401","article-title":"Matrix product state representations","volume":"7","author":"Perez-Garcia","year":"2007","journal-title":"Quantum Info. Comput."},{"key":"mlstabffe8bib25","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.aop.2010.09.012","article-title":"The density matrix renormalization group in the age of matrix product states","volume":"326","author":"Schollw\u00f6ck","year":"2011","journal-title":"Ann. Phys., NY"},{"key":"mlstabffe8bib26","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","article-title":"Tensor-train decomposition","volume":"33","author":"Oseledets","year":"2011","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstabffe8bib27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.101.110501","article-title":"A class of quantum many body systems that can be efficiently simulated","volume":"101","author":"Vidal","year":"2008","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib28","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevB.79.144108","article-title":"Algorithms for entanglement renormalization","volume":"79","author":"Evenbly","year":"2009","journal-title":"Phys. Rev. B"},{"key":"mlstabffe8bib29","article-title":"Algorithms for entanglement renormalization (arXiv version 2)","author":"Vidal","year":"2007"},{"key":"mlstabffe8bib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.109.020604","article-title":"Multigrid algorithms for tensor network states","volume":"109","author":"Dolfi","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib31","author":"Walker","year":"1999"},{"key":"mlstabffe8bib32","article-title":"Quantum criticality with the multi-scale entanglement renormalization ansatz","author":"Evenbly","year":"2011"},{"key":"mlstabffe8bib33","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1103\/PhysRevLett.69.2863","article-title":"Density matrix formulation for quantum renormalization groups","volume":"69","author":"White","year":"1992","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib34","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/scientificamerican0879-158","article-title":"Problems in physics with many scales of length","volume":"241","author":"Wilson","year":"1979","journal-title":"Sci. Am."},{"key":"mlstabffe8bib35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.99.220405","article-title":"Entanglement renormalization","volume":"99","author":"Vidal","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.140403","article-title":"Entanglement renormalization and wavelets","volume":"116","author":"Evenbly","year":"2016","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.97.052314","article-title":"Representation and design of wavelets using unitary circuits","volume":"97","author":"Evenbly","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstabffe8bib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.aop.2019.167998","article-title":"Time-evolution methods for matrix-product states","volume":"411","author":"Paeckel","year":"2019","journal-title":"Ann. Phys., NY"},{"key":"mlstabffe8bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.93.040502","article-title":"Efficient simulation of one-dimensional quantum many-body systems","volume":"93","author":"Vidal","year":"2004","journal-title":"Phys. Rev. Lett."},{"key":"mlstabffe8bib40","author":"","year":"2017"},{"key":"mlstabffe8bib41","article-title":"Generative adversarial network based acoustic scene training set augmentation and selection using SVM-hyperplane","author":"Mun","year":"2017"},{"key":"mlstabffe8bib42","article-title":"Acoustic scene classification using deep convolutional neural network and multiple spectrograms fusion","author":"Weiping","year":"2017"},{"key":"mlstabffe8bib43","article-title":"Recurrent neural network and maximal figure of merit for acoustic event detection","author":"Kukanov","year":"2017"},{"key":"mlstabffe8bib44","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T11:03:38Z","timestamp":1639393418000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abffe8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,14]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,7,14]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abffe8","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,14]]},"assertion":[{"value":"Multi-scale tensor network architecture for machine learning","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-01-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-05-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-07-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}