{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:48:35Z","timestamp":1768319315115,"version":"3.49.0"},"reference-count":70,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"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":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Currently available quantum computers suffer from constraints including hardware noise and a limited number of qubits. As such, variational quantum algorithms that utilise a classical optimiser in order to train a parameterised quantum circuit have drawn significant attention for near-term practical applications of quantum technology. In this work, we take a probabilistic point of view and reformulate the classical optimisation as an approximation of a Bayesian posterior. The posterior is induced by combining the cost function to be minimised with a prior distribution over the parameters of the quantum circuit. We describe a dimension reduction strategy based on a maximum a posteriori point estimate with a Laplace prior. Experiments on the Quantinuum H1-2 computer show that the resulting circuits are faster to execute and less noisy than the circuits trained without the dimension reduction strategy. We subsequently describe a posterior sampling strategy based on stochastic gradient Langevin dynamics. Numerical simulations on three different problems show that the strategy is capable of generating samples from the full posterior and avoiding local optima.<\/jats:p>","DOI":"10.1088\/2632-2153\/acc8b7","type":"journal-article","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T22:38:34Z","timestamp":1680129514000},"page":"025007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Bayesian learning of parameterised quantum circuits"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8656-8734","authenticated-orcid":true,"given":"Samuel","family":"Duffield","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0231-1729","authenticated-orcid":true,"given":"Marcello","family":"Benedetti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1605-9141","authenticated-orcid":false,"given":"Matthias","family":"Rosenkranz","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"mlstacc8b7bib1","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/2\/023023","article-title":"The theory of variational hybrid quantum-classical algorithms","volume":"18","author":"McClean","year":"2016","journal-title":"New J. Phys."},{"key":"mlstacc8b7bib2","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab4eb5","article-title":"Parameterized quantum circuits as machine learning models","volume":"4","author":"Benedetti","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstacc8b7bib3","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s42254-021-00348-9","article-title":"Variational quantum algorithms","volume":"3","author":"Cerezo","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"mlstacc8b7bib4","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.94.015004","article-title":"Noisy intermediate-scale quantum algorithms","volume":"94","author":"Bharti","year":"2022","journal-title":"Rev. Mod. Phys."},{"key":"mlstacc8b7bib5","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1038\/s41467-018-07090-4","article-title":"Barren plateaus in quantum neural network training landscapes","volume":"9","author":"McClean","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstacc8b7bib6","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.1038\/s41467-021-21728-w","article-title":"Cost function dependent barren plateaus in shallow parametrized quantum circuits","volume":"12","author":"Cerezo","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstacc8b7bib7","first-page":"pp 12144","article-title":"Exponentially many local minima in quantum neural networks","author":"You","year":"2021","edition":"ed"},{"key":"mlstacc8b7bib8","article-title":"Beyond barren plateaus:quantum variational algorithms are swamped with traps","author":"Anschuetz","year":"2022"},{"key":"mlstacc8b7bib9","doi-asserted-by":"publisher","first-page":"479","DOI":"10.22331\/q-2021-06-17-479","article-title":"Warm-starting quantum optimization","volume":"5","author":"Egger","year":"2021","journal-title":"Quantum"},{"key":"mlstacc8b7bib10","article-title":"Graph neural network initialisation of quantum approximate optimisation","author":"Jain","year":"2021"},{"key":"mlstacc8b7bib11","article-title":"Gaussian initializations help deep variational quantum circuits escape from the barren plateau","author":"Zhang","year":"2022"},{"key":"mlstacc8b7bib12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41534-019-0240-1","article-title":"Efficient symmetry-preserving state preparation circuits for the variational quantum eigensolver algorithm","volume":"6","author":"Gard","year":"2020","journal-title":"npj Quantum Inf."},{"key":"mlstacc8b7bib13","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1038\/s41567-019-0648-8","article-title":"Quantum convolutional neural networks","volume":"15","author":"Cong","year":"2019","journal-title":"Nat. Phys."},{"key":"mlstacc8b7bib14","article-title":"Exploiting symmetry in variational quantum machine learning","author":"Meyer","year":"2022"},{"key":"mlstacc8b7bib15","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s42484-020-00036-4","article-title":"Layerwise learning for quantum neural networks","volume":"3","author":"Skolik","year":"2021","journal-title":"Quantum Mach. Intell."},{"key":"mlstacc8b7bib16","article-title":"Toward trainability of deep quantum neural networks","author":"Zhang","year":"2021"},{"key":"mlstacc8b7bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.3.020365","article-title":"Avoiding barren plateaus using classical shadows","volume":"3","author":"Sack","year":"2022","journal-title":"PRX Quantum"},{"key":"mlstacc8b7bib18","article-title":"Unsupervised machine learning on a hybrid quantum computer","author":"Otterbach","year":"2017"},{"key":"mlstacc8b7bib19","doi-asserted-by":"publisher","first-page":"eaaw9918","DOI":"10.1126\/sciadv.aaw9918","article-title":"Training of quantum circuits on a hybrid quantum computer","volume":"5","author":"Zhu","year":"2019","journal-title":"Sci. Adv."},{"key":"mlstacc8b7bib20","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41534-021-00452-9","article-title":"Variational quantum algorithm with information sharing","volume":"7","author":"Self","year":"2021","journal-title":"npj Quantum Inf."},{"key":"mlstacc8b7bib21","article-title":"Stochastic gradient line Bayesian optimization: reducing measurement shots in optimizing parameterized quantum circuits","author":"Tamiya","year":"2021"},{"key":"mlstacc8b7bib22","article-title":"Surviving the barren plateau in variational quantum circuits with Bayesian learning initialization","author":"Rad","year":"2022"},{"key":"mlstacc8b7bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.2.010346","article-title":"Minimizing estimation runtime on noisy quantum computers","volume":"2","author":"Wang","year":"2021","journal-title":"PRX Quantum"},{"key":"mlstacc8b7bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.16.044057","article-title":"Variational inference with a quantum computer","volume":"16","author":"Benedetti","year":"2021","journal-title":"Phys. Rev. Appl."},{"key":"mlstacc8b7bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033125","article-title":"Expressive power of parametrized quantum circuits","volume":"2","author":"Du","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstacc8b7bib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.89.062315","article-title":"Quantum inference on Bayesian networks","volume":"89","author":"Low","year":"2014","journal-title":"Phys. Rev. A"},{"key":"mlstacc8b7bib27","first-page":"pp 193","article-title":"Adaptive quantum simulated annealing for Bayesian inference and estimating partition functions","author":"Harrow","year":"2020"},{"key":"mlstacc8b7bib28","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1142\/S0217979295000148","article-title":"Quantum Bayesian nets","volume":"09","author":"Tucci","year":"1995","journal-title":"Int. J. Mod. Phys. B"},{"key":"mlstacc8b7bib29","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1016\/j.aop.2007.10.001","article-title":"Quantum graphical models and belief propagation","volume":"323","author":"Leifer","year":"2008","journal-title":"Ann. Phys., NY"},{"key":"mlstacc8b7bib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.7.031021","article-title":"Quantum common causes and quantum causal models","volume":"7","author":"Allen","year":"2017","journal-title":"Phys. Rev. X"},{"key":"mlstacc8b7bib31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.140502","article-title":"Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms","volume":"126","author":"Harrow","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstacc8b7bib32","doi-asserted-by":"publisher","first-page":"314","DOI":"10.22331\/q-2020-08-31-314","article-title":"Stochastic gradient descent for hybrid quantum-classical optimization","volume":"4","author":"Sweke","year":"2020","journal-title":"Quantum"},{"key":"mlstacc8b7bib33","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1111\/rssb.12158","article-title":"A general framework for updating belief distributions","volume":"78","author":"Bissiri","year":"2016","journal-title":"J. R. Stat. Soc. B"},{"key":"mlstacc8b7bib34","article-title":"Generalized Bayesian likelihood-free inference using scoring rules estimators","author":"Pacchiardi","year":"2021"},{"key":"mlstacc8b7bib35","author":"Brooks","year":"2011"},{"key":"mlstacc8b7bib36","author":"Chopin","year":"2020"},{"key":"mlstacc8b7bib37","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: a review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"J. Am. Stat. Assoc."},{"key":"mlstacc8b7bib38","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. B"},{"key":"mlstacc8b7bib39","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1561\/2400000003","article-title":"Proximal algorithms","volume":"1","author":"Parikh","year":"2014","journal-title":"Found. Trends Optim."},{"key":"mlstacc8b7bib40","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1137\/050626090","article-title":"Signal recovery by proximal forward-backward splitting","volume":"4","author":"Combettes","year":"2005","journal-title":"Multiscale Model. Simul."},{"key":"mlstacc8b7bib41","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1162\/neco.1995.7.1.117","article-title":"Bayesian regularization and pruning using a Laplace prior","volume":"7","author":"Williams","year":"1995","journal-title":"Neural Comput."},{"key":"mlstacc8b7bib42","article-title":"The dilemma of quantum neural networks","author":"Qian","year":"2021"},{"key":"mlstacc8b7bib43","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1214\/15-STS530","article-title":"Proximal algorithms in statistics and machine learning","volume":"30","author":"Polson","year":"2015","journal-title":"Stat. Sci."},{"key":"mlstacc8b7bib44","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1214\/009053604000001147","article-title":"Spike and slab variable selection: frequentist and Bayesian strategies","volume":"33","author":"Ishwaran","year":"2005","journal-title":"Ann. Stat."},{"key":"mlstacc8b7bib45","first-page":"73","article-title":"Handling sparsity via the horseshoe","author":"Carvalho","year":"2009","edition":"ed"},{"key":"mlstacc8b7bib46","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1214\/07-AOS574","article-title":"The pseudo-marginal approach for efficient Monte Carlo computations","volume":"37","author":"Andrieu","year":"2009","journal-title":"Ann. Stat."},{"key":"mlstacc8b7bib47","first-page":"pp 681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"Welling","year":"2011"},{"key":"mlstacc8b7bib48","article-title":"A Complete recipe for stochastic gradient MCMC","volume":"vol 28","author":"Ma","year":"2015","edition":"ed"},{"key":"mlstacc8b7bib49","first-page":"193","article-title":"Consistency and fluctuations for stochastic gradient Langevin dynamics","volume":"17","author":"Teh","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacc8b7bib50","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"key":"mlstacc8b7bib51","doi-asserted-by":"publisher","first-page":"583","DOI":"10.3390\/e20080583","article-title":"Information perspective to probabilistic modeling: Boltzmann machines versus born machines","volume":"20","author":"Cheng","year":"2018","journal-title":"Entropy"},{"key":"mlstacc8b7bib52","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.118.150503","article-title":"Hybrid quantum-classical approach to quantum optimal control","volume":"118","author":"Li","year":"2017","journal-title":"Phys. Rev. Lett."},{"key":"mlstacc8b7bib53","article-title":"Qujax: simulating quantum circuits with JAX","author":"Duffield","year":"2022"},{"key":"mlstacc8b7bib54","author":"Sachdev","year":"2011","edition":"2nd edn"},{"key":"mlstacc8b7bib55","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1080\/01621459.1988.10478683","article-title":"Philatelic mixtures and multimodal densities","volume":"83","author":"Izenman","year":"1988","journal-title":"J. Am. Stat. Assoc."},{"key":"mlstacc8b7bib56","article-title":"Generalized variational inference: three arguments for deriving new posteriors","author":"Knoblauch","year":"2019"},{"key":"mlstacc8b7bib57","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacc8b7bib58","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.062324","article-title":"Differentiable learning of quantum circuit born machines","volume":"98","author":"Liu","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstacc8b7bib59","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1038\/s41586-021-03318-4","article-title":"Demonstration of the trapped-ion quantum CCD computer architecture","volume":"592","author":"Pino","year":"2021","journal-title":"Nature"},{"key":"mlstacc8b7bib60","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab8e92","article-title":"t | ket \u27e9 : a retargetable compiler for NISQ devices","volume":"6","author":"Sivarajah","year":"2020","journal-title":"Quantum Sci. Technol."},{"key":"mlstacc8b7bib61","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate o(1\/k2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Proc. USSR Acad. Sci."},{"key":"mlstacc8b7bib62","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015","edition":"ed"},{"key":"mlstacc8b7bib63","first-page":"pp 2111","article-title":"Convergence analysis of proximal gradient with momentum for nonconvex optimization","author":"Li","year":"2017","edition":"ed"},{"key":"mlstacc8b7bib64","first-page":"pp 1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","author":"Chen","year":"2014","edition":"ed"},{"key":"mlstacc8b7bib65","doi-asserted-by":"publisher","first-page":"A712","DOI":"10.1137\/15M102318X","article-title":"Adaptive thermostats for noisy gradient systems","volume":"38","author":"Leimkuhler","year":"2016","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstacc8b7bib66","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1146\/annurev-statistics-030718-105212","article-title":"Approximate Bayesian computation","volume":"6","author":"Beaumont","year":"2019","journal-title":"Annu. Rev. Stat. Appl."},{"key":"mlstacc8b7bib67","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/abd891","article-title":"Large gradients via correlation in random parameterized quantum circuits","volume":"6","author":"Volkoff","year":"2021","journal-title":"Quantum Sci. Technol."},{"key":"mlstacc8b7bib68","volume":"vol 2","author":"Mardia","year":"2000"},{"key":"mlstacc8b7bib69","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","author":"Wilson","year":"2020"},{"key":"mlstacc8b7bib70","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2022.109523","article-title":"Ensemble Kalman inversion for general likelihoods","volume":"187","author":"Duffield","year":"2022","journal-title":"Stat. Probab. Lett."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T11:15:58Z","timestamp":1681298158000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc8b7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":70,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,4,12]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acc8b7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,12]]},"assertion":[{"value":"Bayesian learning of parameterised quantum circuits","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-11-25","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-03-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-04-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}