{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T09:04:09Z","timestamp":1793178249643,"version":"4.5.0"},"reference-count":31,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2020,12,29]],"date-time":"2020-12-29T00:00:00Z","timestamp":1609200000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,12,29]],"date-time":"2020-12-29T00:00:00Z","timestamp":1609200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>A notion of quantum natural evolution strategies is introduced, which provides a geometric synthesis of a number of known quantum\/classical algorithms for performing classical black-box optimization. The recent work of Gomes <jats:italic>et al<\/jats:italic> (2019 arXiv:1910.10675) on heuristic combinatorial optimization using neural quantum states is pedagogically reviewed in this context, emphasizing the connection with natural evolution strategies (NES). The algorithmic framework is illustrated for approximate combinatorial optimization problems, and a systematic strategy is found for improving the approximation ratios. In particular, it is found that NES can achieve approximation ratios competitive with widely used heuristic algorithms for Max-Cut, at the expense of increased computation time.<\/jats:p>","DOI":"10.1088\/2632-2153\/abcb50","type":"journal-article","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T05:49:25Z","timestamp":1605678565000},"page":"02LT01","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Natural evolution strategies and variational Monte Carlo"],"prefix":"10.1088","volume":"2","author":[{"given":"Tianchen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Carleo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7467-6001","authenticated-orcid":false,"given":"James","family":"Stokes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2294-7233","authenticated-orcid":false,"given":"Shravan","family":"Veerapaneni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2020,12,29]]},"reference":[{"key":"mlstabcb50bib1","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s10208-005-0179-9","article-title":"Trust-region methods on Riemannian manifolds","volume":"7","author":"Absil","year":"2007","journal-title":"Found. Comput. Math."},{"key":"mlstabcb50bib2","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1080\/23307706.2017.1397554","article-title":"A rewriting system for convex optimization problems","volume":"5","author":"Agrawal","year":"2018","journal-title":"J. Control Decision"},{"key":"mlstabcb50bib3","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","article-title":"Natural gradient works efficiently in learning","volume":"10","author":"Amari","year":"1998","journal-title":"Neural Comput."},{"key":"mlstabcb50bib4","first-page":"1455","article-title":"Manopt, a Matlab toolbox for optimization on manifolds","volume":"15","author":"Boumal","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabcb50bib5","first-page":"2757","article-title":"The non-convex Burer\u2013Monteiro approach works on smooth semidefinite programs","volume":"vol 29","author":"Boumal","year":"2016"},{"key":"mlstabcb50bib6","first-page":"2003","article-title":"A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization","volume":"95","author":"Burer","year":"2001","journal-title":"Mathematical Programming Ser. B"},{"key":"mlstabcb50bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2019.100311","article-title":"Netket: a machine learning toolkit for many-body quantum systems","volume":"10","author":"Carleo","year":"2019","journal-title":"SoftwareX"},{"key":"mlstabcb50bib8","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1126\/science.aag2302","article-title":"Solving the quantum many-body problem with artificial neural networks","volume":"355","author":"Carleo","year":"2017","journal-title":"Science"},{"key":"mlstabcb50bib9","first-page":"1","article-title":"CVXPY: a Python-embedded modeling language for convex optimization","volume":"17","author":"Diamond","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabcb50bib10","article-title":"A quantum approximate optimization algorithm","author":"Farhi","year":"2014"},{"key":"mlstabcb50bib11","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1145\/227683.227684","article-title":"Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming","volume":"42","author":"Goemans","year":"1995","journal-title":"J. ACM (JACM)"},{"key":"mlstabcb50bib12","article-title":"Classical quantum optimization with neural network quantum states","author":"Gomes","year":"2019"},{"key":"mlstabcb50bib13","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.1137\/080731359","article-title":"Low-rank optimization on the cone of positive semidefinite matrices","volume":"20","author":"Journ\u00e9e","year":"2010","journal-title":"SIAM J. Optim."},{"key":"mlstabcb50bib14","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"mlstabcb50bib15","article-title":"Quantum natural gradient generalised to non-unitary circuits:","author":"Koczor","year":"2019"},{"key":"mlstabcb50bib16","first-page":"2081","article-title":"An information geometry perspective on estimation of distribution algorithms: boundary analysis","author":"Malag\u00f2","year":"2008"},{"key":"mlstabcb50bib17","first-page":"230","article-title":"Towards the geometry of estimation of distribution algorithms based on the exponential family","author":"Malag\u00f2","year":"2011"},{"key":"mlstabcb50bib18","doi-asserted-by":"publisher","first-page":"A442","DOI":"10.1103\/PhysRev.138.A442","article-title":"Ground state of liquid he4","volume":"138","author":"McMillan","year":"1965","journal-title":"Phys. Rev."},{"key":"mlstabcb50bib19","author":"Mitzenmacher","year":"2005"},{"key":"mlstabcb50bib20","first-page":"415","article-title":"Expressive power and approximation errors of restricted boltzmann machines","author":"Mont\u00fafar","year":"2011"},{"key":"mlstabcb50bib21","first-page":"564","article-title":"Information-geometric optimization algorithms: a unifying picture via invariance principles","volume":"18","author":"Ollivier","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabcb50bib22","first-page":"83","author":"Rechenberg","year":"1978"},{"key":"mlstabcb50bib23","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"mlstabcb50bib24","volume":"vol 1","author":"Schwefel","year":"1977"},{"key":"mlstabcb50bib25","doi-asserted-by":"publisher","first-page":"4558","DOI":"10.1103\/PhysRevLett.80.4558","article-title":"Green function Monte Carlo with stochastic reconfiguration","volume":"80","author":"Sorella","year":"1998","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcb50bib26","article-title":"Quantum natural gradient","author":"Stokes","year":"2019"},{"key":"mlstabcb50bib27","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.3390\/e21121236","article-title":"Probabilistic modeling with matrix product states","volume":"21","author":"Stokes","year":"2019","journal-title":"Entropy"},{"key":"mlstabcb50bib28","article-title":"On the importance of initialization and momentum in deep learning","author":"Sutskever","year":"2013"},{"key":"mlstabcb50bib29","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"Wierstra","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabcb50bib30","doi-asserted-by":"publisher","first-page":"191","DOI":"10.22331\/q-2019-10-07-191","article-title":"Theory of variational quantum simulation","volume":"3","author":"Yuan","year":"2019","journal-title":"Quantum"},{"key":"mlstabcb50bib31","article-title":"Adadelta: an adaptive learning rate method","author":"Zeiler","year":"2012"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T15:18:50Z","timestamp":1641914330000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcb50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,29]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,12,29]]},"published-print":{"date-parts":[[2021,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abcb50","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,29]]},"assertion":[{"value":"Natural evolution strategies and variational Monte Carlo","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 2020 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-05-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-11-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}