{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:25:43Z","timestamp":1775535943649,"version":"3.50.1"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"EPFL Lausanne"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A new paradigm for data science has emerged, with quantum data, quantum models, and quantum computational devices. This field, called quantum machine learning (QML), aims to achieve a speedup over traditional machine learning for data analysis. However, its success usually hinges on efficiently training the parameters in quantum neural networks, and the field of QML is still lacking theoretical scaling results for their trainability. Some trainability results have been proven for a closely related field called variational quantum algorithms (VQAs). While both fields involve training a parametrized quantum circuit, there are crucial differences that make the results for one setting not readily applicable to the other. In this work, we bridge the two frameworks and show that gradient scaling results for VQAs can also be applied to study the gradient scaling of QML models. Our results indicate that features deemed detrimental for VQA trainability can also lead to issues such as barren plateaus in QML. Consequently, our work has implications for several QML proposals in the literature. In addition, we provide theoretical and numerical evidence that QML models exhibit further trainability issues not present in VQAs, arising from the use of a training dataset. We refer to these as dataset-induced barren plateaus. These results are most relevant when dealing with classical data, as here the choice of embedding scheme (i.e., the map between classical data and quantum states) can greatly affect the gradient scaling.<\/jats:p>","DOI":"10.1007\/s42484-023-00103-6","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T14:39:49Z","timestamp":1684161589000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Subtleties in the trainability of quantum machine learning models"],"prefix":"10.1007","volume":"5","author":[{"given":"Supanut","family":"Thanasilp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samson","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nhat Anh","family":"Nghiem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Coles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Cerezo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,15]]},"reference":[{"key":"103_CR1","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16), pp 265\u2013283"},{"issue":"6","key":"103_CR2","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s43588-021-00084-1","volume":"1","author":"A Abbas","year":"2021","unstructured":"Abbas A, Sutter D, Zoufal C, Lucchi A, Figalli A, Woerner S (2021) The power of quantum neural networks. Nat Comput Sci 1(6):403\u2013409","journal-title":"Nat Comput Sci"},{"issue":"1","key":"103_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-27922-0","volume":"13","author":"D Aharonov","year":"2022","unstructured":"Aharonov D, Cotler J, Qi X-L (2022) Quantum algorithmic measurement. Nat Commun 13(1):1\u20139","journal-title":"Nat Commun"},{"issue":"2","key":"103_CR4","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S-I Amari","year":"1998","unstructured":"Amari S-I (1998) Natural gradient works efficiently in learning. Neur Comput 10(2):251\u2013276","journal-title":"Neur Comput"},{"key":"103_CR5","doi-asserted-by":"crossref","unstructured":"Anschuetz E, Olson J, Aspuru-Guzik A, Cao Y (2019) Variational quantum factoring. In: International Workshop on Quantum Technology and Optimization Problems. Springer, pp 74\u201385","DOI":"10.1007\/978-3-030-14082-3_7"},{"key":"103_CR6","doi-asserted-by":"publisher","first-page":"7760","DOI":"10.1038\/s41467-022-35364-5","volume":"13","author":"ER Anschuetz","year":"2022","unstructured":"Anschuetz ER, et al. (2022) Quantum variational algorithms are swamped with traps. Nat Commun 13:7760","journal-title":"Nat Commun"},{"key":"103_CR7","doi-asserted-by":"publisher","first-page":"558","DOI":"10.22331\/q-2021-10-05-558","volume":"5","author":"A Arrasmith","year":"2021","unstructured":"Arrasmith A, Cerezo M, Czarnik P, Cincio L, Coles P J (2021) Effect of barren plateaus on gradient-free optimization. Quantum 5:558","journal-title":"Quantum"},{"key":"103_CR8","doi-asserted-by":"crossref","unstructured":"Arrasmith A, Holmes Z, Cerezo M, Coles P J (2021) Equivalence of quantum barren plateaus to cost concentration and narrow gorges. arXiv:https:\/\/arxiv.org\/abs\/2104.05868","DOI":"10.1088\/2058-9565\/ac7d06"},{"issue":"4","key":"103_CR9","doi-asserted-by":"publisher","first-page":"040321","DOI":"10.1103\/PRXQuantum.2.040321","volume":"2","author":"L Banchi","year":"2021","unstructured":"Banchi L, Pereira J, Pirandola S (2021) Generalization in quantum machine learning: a quantum information perspective. PRX Quantum 2(4):040321","journal-title":"PRX Quantum"},{"key":"103_CR10","unstructured":"Bausch J (2020) Recurrent quantum neural networks. arXiv:https:\/\/arxiv.org\/abs\/2006.14619"},{"issue":"1","key":"103_CR11","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1038\/s41467-020-14454-2","volume":"11","author":"K Beer","year":"2020","unstructured":"Beer K, Bondarenko D, Farrelly T, Osborne T J, Salzmann R, Scheiermann D, Wolf R (2020) Training deep quantum neural networks. Nat Commun 11(1):808","journal-title":"Nat Commun"},{"issue":"7671","key":"103_CR12","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/nature23474","volume":"549","author":"J Biamonte","year":"2017","unstructured":"Biamonte J, Wittek P, Pancotti N, Rebentrost P, Wiebe N, Lloyd S (2017) Quantum machine learning. Nature 549(7671):195\u2013202","journal-title":"Nature"},{"key":"103_CR13","unstructured":"Bilkis M, Cerezo M, Verdon G, Coles P J, Cincio L (2021) A semi-agnostic ansatz with variable structure for quantum machine learning. arXiv:https:\/\/arxiv.org\/abs\/2103.06712"},{"issue":"01","key":"103_CR14","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1142\/S1230161210000047","volume":"17","author":"FGSL Brandao","year":"2010","unstructured":"Brandao FGSL, Horodecki M (2010) On hastings\u2019 counterexamples to the minimum output entropy additivity conjecture. Open Syst Inform Dyn 17(01):31\u201352","journal-title":"Open Syst Inform Dyn"},{"key":"103_CR15","unstructured":"Bravo-Prieto C, LaRose R, Cerezo M, Subasi Y, Cincio L, Coles P (2019) Variational quantum linear solver. arXiv:https:\/\/arxiv.org\/abs\/1909.05820"},{"issue":"2126","key":"103_CR16","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1098\/rspa.2010.0301","volume":"467","author":"MJ Bremner","year":"2011","unstructured":"Bremner M J, Jozsa R, Shepherd D J (2011) Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy. Proc R Soc A: Math Phys Eng Sci 467(2126):459\u2013472","journal-title":"Proc R Soc A: Math Phys Eng Sci"},{"key":"103_CR17","doi-asserted-by":"crossref","unstructured":"Caro MC, et al. (2022a) Out-of-distribution generalization for learning quantum dynamics, arxiv:https:\/\/arxiv.org\/abs\/2204.10268","DOI":"10.2172\/2377336"},{"key":"103_CR18","doi-asserted-by":"crossref","unstructured":"Caro MC, et al. (2022b) Generalization in quantum machine learning from few training data. Nat Commun 13:4919","DOI":"10.1038\/s41467-022-32550-3"},{"issue":"1","key":"103_CR19","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s42254-021-00348-9","volume":"3","author":"M Cerezo","year":"2021","unstructured":"Cerezo M, Arrasmith A, Babbush R, Benjamin S C, Endo S, Fujii K, McClean J R, Mitarai K, Yuan X, Cincio L, Coles P J (2021) Variational quantum algorithms. Nat Rev Phys 3 (1):625\u2013644","journal-title":"Nat Rev Phys"},{"issue":"2","key":"103_CR20","doi-asserted-by":"publisher","first-page":"035006","DOI":"10.1088\/2058-9565\/abf51a","volume":"6","author":"M Cerezo","year":"2021","unstructured":"Cerezo M, Coles P J (2021) Higher order derivatives of quantum neural networks with barren plateaus. Quant Sci Technol 6(2):035006","journal-title":"Quant Sci Technol"},{"issue":"1","key":"103_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-21728-w","volume":"12","author":"M Cerezo","year":"2021","unstructured":"Cerezo M, Sone A, Volkoff T, Cincio L, Coles P J (2021) Cost function dependent barren plateaus in shallow parametrized quantum circuits. Nat Commun 12(1):1\u201312","journal-title":"Nat Commun"},{"issue":"1","key":"103_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41534-019-0235-y","volume":"6","author":"C Cirstoiu","year":"2020","unstructured":"Cirstoiu C, Holmes Z, Iosue J, Cincio L, Coles P J, Sornborger A (2020) Variational fast forwarding for quantum simulation beyond the coherence time. npj Quant Inform 6(1):1\u201310","journal-title":"npj Quant Inform"},{"key":"103_CR23","unstructured":"Commeau B, Cerezo M, Holmes Z, Cincio L, Coles P J, Sornborger A (2020) Variational hamiltonian diagonalization for dynamical quantum simulation. arXiv:https:\/\/arxiv.org\/abs\/2009.02559"},{"issue":"12","key":"103_CR24","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1038\/s41567-019-0648-8","volume":"15","author":"I Cong","year":"2019","unstructured":"Cong I, Choi S, Lukin M D (2019) Quantum convolutional neural networks. Nat Phys 15 (12):1273\u20131278","journal-title":"Nat Phys"},{"key":"103_CR25","unstructured":"Du Y, Huang T, You S, Hsieh M-H, Tao D (2020) Quantum circuit architecture search: error mitigation and trainability enhancement for variational quantum solvers. arXiv:https:\/\/arxiv.org\/abs\/2010.10217"},{"issue":"8","key":"103_CR26","doi-asserted-by":"publisher","first-page":"080506","DOI":"10.1103\/PhysRevLett.128.080506","volume":"128","author":"Y Du","year":"2022","unstructured":"Du Y, Tu Z, Yuan X, Tao D (2022) An efficient measure for the expressivity of variational quantum algorithms. Phys Rev Lett 128(8):080506","journal-title":"Phys Rev Lett"},{"issue":"1","key":"103_CR27","doi-asserted-by":"publisher","first-page":"010501","DOI":"10.1103\/PhysRevLett.125.010501","volume":"125","author":"S Endo","year":"2020","unstructured":"Endo S, Sun J, Li Y, Benjamin S C, Yuan X (2020) Variational quantum simulation of general processes. Phys Rev Lett 125(1):010501","journal-title":"Phys Rev Lett"},{"key":"103_CR28","unstructured":"Farhi E, Neven H (2018) Classification with quantum neural networks on near term processors. arXiv:https:\/\/arxiv.org\/abs\/1802.06002"},{"issue":"1","key":"103_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-019-10988-2","volume":"10","author":"HR Grimsley","year":"2019","unstructured":"Grimsley H R, Economou S E, Barnes E, Mayhall N J (2019) An adaptive variational algorithm for exact molecular simulations on a quantum computer. Nat Commun 10(1):1\u20139","journal-title":"Nat Commun"},{"key":"103_CR30","unstructured":"Haug T, Kim MS (2021) Optimal training of variational quantum algorithms without barren plateaus. arXiv:https:\/\/arxiv.org\/abs\/2104.14543"},{"issue":"7747","key":"103_CR31","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1038\/s41586-019-0980-2","volume":"567","author":"V Havl\u00ed\u010dek","year":"2019","unstructured":"Havl\u00ed\u010dek V, C\u00f3rcoles A D, Temme K, Harrow A W, Kandala A, Chow J M, Gambetta J M (2019) Supervised learning with quantum-enhanced feature spaces. Nature 567(7747):209\u2013212","journal-title":"Nature"},{"issue":"19","key":"103_CR32","doi-asserted-by":"publisher","first-page":"190501","DOI":"10.1103\/PhysRevLett.126.190501","volume":"126","author":"Z Holmes","year":"2021","unstructured":"Holmes Z, Arrasmith A, Yan B, Coles P J, Albrecht A, Sornborger A T (2021) Barren plateaus preclude learning scramblers. Phys Rev Lett 126(19):190501","journal-title":"Phys Rev Lett"},{"key":"103_CR33","doi-asserted-by":"publisher","first-page":"010313","DOI":"10.1103\/PRXQuantum.3.010313","volume":"3","author":"Z Holmes","year":"2021","unstructured":"Holmes Z, Sharma K, Cerezo M, Coles P J (2021) Connecting ansatz expressibility to gradient magnitudes and barren plateaus. PRX Quant 3:010313","journal-title":"PRX Quant"},{"key":"103_CR34","unstructured":"Huang H-Y, Bharti K, Rebentrost P (2019) Near-term quantum algorithms for linear systems of equations. arXiv:https:\/\/arxiv.org\/abs\/1909.07344"},{"issue":"1","key":"103_CR35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-20314-w","volume":"12","author":"H-Y Huang","year":"2021","unstructured":"Huang H-Y, Broughton M, Mohseni M, Babbush R, Boixo S, Neven H, McClean J R (2021) Power of data in quantum machine learning. Nat Commun 12(1):1\u20139","journal-title":"Nat Commun"},{"key":"103_CR36","doi-asserted-by":"publisher","first-page":"190505","DOI":"10.1103\/PhysRevLett.126.190505","volume":"126","author":"H-Y Huang","year":"2021","unstructured":"Huang H-Y, Kueng R, Preskill J (2021) Information-theoretic bounds on quantum advantage in machine learning. Phys Rev Lett 126:190505","journal-title":"Phys Rev Lett"},{"key":"103_CR37","doi-asserted-by":"crossref","unstructured":"Hubregtsen T, Wierichs D, Gil-Fuster E, Derks Peter-Jan HS, Faehrmann P K, Meyer J J (2021) Training quantum embedding kernels on near-term quantum computers. arXiv:https:\/\/arxiv.org\/abs\/2105.02276","DOI":"10.1103\/PhysRevA.106.042431"},{"issue":"2","key":"103_CR38","doi-asserted-by":"publisher","first-page":"025011","DOI":"10.1088\/2058-9565\/abdbc9","volume":"6","author":"P Huembeli","year":"2021","unstructured":"Huembeli P, Dauphin A (2021) Characterizing the loss landscape of variational quantum circuits. Quant Sci Technol 6(2):025011","journal-title":"Quant Sci Technol"},{"key":"103_CR39","unstructured":"Hur T, Kim L, Park D K (2021) Quantum convolutional neural network for classical data classification. arXiv:https:\/\/arxiv.org\/abs\/2108.00661"},{"key":"103_CR40","unstructured":"Jerbi S, et al. (2023) The power and limitations of learning quantum dynamics incoherently, arXiv:https:\/\/arxiv.org\/abs\/2303.12834"},{"key":"103_CR41","doi-asserted-by":"crossref","unstructured":"Jolliffe I (2005) Principal component analysis. Encyclopedia of statistics in behavioral science","DOI":"10.1002\/0470013192.bsa501"},{"key":"103_CR42","doi-asserted-by":"publisher","first-page":"140","DOI":"10.22331\/q-2019-05-13-140","volume":"3","author":"S Khatri","year":"2019","unstructured":"Khatri S, LaRose R, Poremba A, Cincio L, Sornborger A T, Coles P J (2019) Quantum-assisted quantum compiling. Quantum 3:140","journal-title":"Quantum"},{"key":"103_CR43","unstructured":"Kiani B T, De Palma G, Marvian M, Liu Z-W, Lloyd S (2021) Quantum earth mover\u2019s distance: a new approach to learning quantum data. arXiv:https:\/\/arxiv.org\/abs\/2101.03037"},{"key":"103_CR44","unstructured":"Kieferova M, Carlos O M, Wiebe N (2021) Quantum generative training using r\u2216\u2019enyi divergences. arXiv:https:\/\/arxiv.org\/abs\/2106.09567"},{"key":"103_CR45","unstructured":"Kingma D P, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR)"},{"key":"103_CR46","first-page":"12661","volume":"34","author":"JM K\u00fcbler","year":"2021","unstructured":"K\u00fcbler J M, Buchholz S, Sch\u00f6lkopf B (2021) The inductive bias of quantum kernels. Adv Neur Inform Process Syst 34:12661\u201312673","journal-title":"Adv Neur Inform Process Syst"},{"key":"103_CR47","doi-asserted-by":"crossref","unstructured":"Larocca M, Czarnik P, Sharma K, Muraleedharan G, Coles P J, Cerezo M (2021) Diagnosing barren plateaus with tools from quantum optimal control. arXiv:https:\/\/arxiv.org\/abs\/2105.14377","DOI":"10.22331\/q-2022-09-29-824"},{"key":"103_CR48","unstructured":"Larocca M, Ju N, Garc\u00eda-Mart\u00edn D, Coles P J, Cerezo M (2021) Theory of overparametrization in quantum neural networks. arXiv:https:\/\/arxiv.org\/abs\/2109.11676"},{"issue":"3","key":"103_CR49","doi-asserted-by":"publisher","first-page":"032420","DOI":"10.1103\/PhysRevA.102.032420","volume":"102","author":"R LaRose","year":"2020","unstructured":"LaRose R, Coyle B (2020) Robust data encodings for quantum classifiers. Phys Rev A 102 (3):032420","journal-title":"Phys Rev A"},{"key":"103_CR50","unstructured":"LeCun Y (1998) The mnist database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"103_CR51","unstructured":"Ledoux M (2001) The concentration of measure phenomenon. Number 89. American Mathematical Soc"},{"key":"103_CR52","first-page":"021050","volume":"7","author":"Y Li","year":"2017","unstructured":"Li Y, Benjamin S C (2017) Efficient variational quantum simulator incorporating active error minimization. Phys Rev X 7:021050","journal-title":"Phys Rev X"},{"key":"103_CR53","doi-asserted-by":"crossref","unstructured":"Liu Y, Arunachalam S, Temme K (2021) A rigorous and robust quantum speed-up in supervised machine learning. Nat Phys, 1\u20135","DOI":"10.1038\/s41567-021-01287-z"},{"key":"103_CR54","doi-asserted-by":"crossref","unstructured":"Liu Z, Yu L-W, Duan L-M, Deng D-L (2021) The presence and absence of barren plateaus in tensor-network based machine learning. arXiv:https:\/\/arxiv.org\/abs\/2108.08312","DOI":"10.1103\/PhysRevLett.129.270501"},{"key":"103_CR55","unstructured":"Lloyd S, Schuld M, Ijaz A, Izaac J, Killoran N (2020) Quantum embeddings for machine learning. arXiv:https:\/\/arxiv.org\/abs\/2001.03622"},{"issue":"4","key":"103_CR56","doi-asserted-by":"publisher","first-page":"040316","DOI":"10.1103\/PRXQuantum.2.040316","volume":"2","author":"CO Marrero","year":"2020","unstructured":"Marrero C O, Kieferov\u00e1 M, Wiebe N (2020) Entanglement induced barren plateaus. PRX Quant 2(4):040316","journal-title":"PRX Quant"},{"issue":"1","key":"103_CR57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07090-4","volume":"9","author":"JR McClean","year":"2018","unstructured":"McClean J R, Boixo S, Smelyanskiy V N, Babbush R, Neven H (2018) Barren plateaus in quantum neural network training landscapes. Nat Commun 9(1):1\u20136","journal-title":"Nat Commun"},{"issue":"3","key":"103_CR58","doi-asserted-by":"publisher","first-page":"032309","DOI":"10.1103\/PhysRevA.98.032309","volume":"98","author":"K Mitarai","year":"2018","unstructured":"Mitarai K, Negoro M, Kitagawa M, Fujii K (2018) Quantum circuit learning. Phys Rev A 98(3):032309","journal-title":"Phys Rev A"},{"issue":"3","key":"103_CR59","doi-asserted-by":"publisher","first-page":"033090","DOI":"10.1103\/PhysRevResearch.3.033090","volume":"3","author":"TL Patti","year":"2021","unstructured":"Patti T L, Najafi K, Gao X, Yelin S F (2021) Entanglement devised barren plateau mitigation. Phys Rev Res 3(3):033090","journal-title":"Phys Rev Res"},{"key":"103_CR60","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"103_CR61","doi-asserted-by":"crossref","unstructured":"Perrier E, Youssry A, Ferrie C (2021) Qdataset: quantum datasets for machine learning. arXiv:https:\/\/arxiv.org\/abs\/2108.06661","DOI":"10.1038\/s41597-022-01639-1"},{"issue":"1","key":"103_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms5213","volume":"5","author":"A Peruzzo","year":"2014","unstructured":"Peruzzo A, McClean J, Shadbolt P, Yung M-H, Zhou X-Q, Love P J, Aspuru-Guzik A, O\u2019brien J L (2014) A variational eigenvalue solver on a photonic quantum processor. Nat Commun 5(1):1\u20137","journal-title":"Nat Commun"},{"issue":"4","key":"103_CR63","first-page":"041011","volume":"11","author":"A Pesah","year":"2021","unstructured":"Pesah A, Cerezo M, Wang S, Volkoff T, Sornborger A T, Coles P J (2021) Absence of barren plateaus in quantum convolutional neural networks. Phys Rev X 11(4):041011","journal-title":"Phys Rev X"},{"key":"103_CR64","doi-asserted-by":"publisher","first-page":"79","DOI":"10.22331\/q-2018-08-06-79","volume":"2","author":"J Preskill","year":"2018","unstructured":"Preskill J (2018) Quantum computing in the nisq era and beyond. Quantum 2:79","journal-title":"Quantum"},{"key":"103_CR65","unstructured":"Schatzki L, Arrasmith A, Coles P J, Cerezo M (2021) Entangled datasets for quantum machine learning. arXiv:https:\/\/arxiv.org\/abs\/2109.03400"},{"issue":"3","key":"103_CR66","doi-asserted-by":"publisher","first-page":"032331","DOI":"10.1103\/PhysRevA.99.032331","volume":"99","author":"M Schuld","year":"2019","unstructured":"Schuld M, Bergholm V, Gogolin C, Izaac J, Killoran N (2019) Evaluating analytic gradients on quantum hardware. Phys Rev A 99(3):032331","journal-title":"Phys Rev A"},{"issue":"3","key":"103_CR67","doi-asserted-by":"publisher","first-page":"032308","DOI":"10.1103\/PhysRevA.101.032308","volume":"101","author":"M Schuld","year":"2020","unstructured":"Schuld M, Bocharov A, Svore K M, Wiebe N (2020) Circuit-centric quantum classifiers. Phys Rev A 101(3):032308","journal-title":"Phys Rev A"},{"issue":"11","key":"103_CR68","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1007\/s11128-014-0809-8","volume":"13","author":"M Schuld","year":"2014","unstructured":"Schuld M, Sinayskiy I, Petruccione F (2014) The quest for a quantum neural network. Quantum Inf Process 13(11):2567\u2013 2586","journal-title":"Quantum Inf Process"},{"issue":"2","key":"103_CR69","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1080\/00107514.2014.964942","volume":"56","author":"M Schuld","year":"2015","unstructured":"Schuld M, Sinayskiy I, Petruccione F (2015) An introduction to quantum machine learning. Contemp Phys 56(2):172\u2013185","journal-title":"Contemp Phys"},{"issue":"18","key":"103_CR70","doi-asserted-by":"publisher","first-page":"180505","DOI":"10.1103\/PhysRevLett.128.180505","volume":"128","author":"K Sharma","year":"2022","unstructured":"Sharma K, Cerezo M, Cincio L, Coles P J (2022) Trainability of dissipative perceptron-based quantum neural networks. Phys Rev Lett 128(18):180505","journal-title":"Phys Rev Lett"},{"issue":"4","key":"103_CR71","doi-asserted-by":"publisher","first-page":"043006","DOI":"10.1088\/1367-2630\/ab784c","volume":"22","author":"K Sharma","year":"2020","unstructured":"Sharma K, Khatri S, Cerezo M, Coles P J (2020) Noise resilience of variational quantum compiling. New J Phys 22(4):043006","journal-title":"New J Phys"},{"issue":"4","key":"103_CR72","doi-asserted-by":"publisher","first-page":"043364","DOI":"10.1103\/PhysRevResearch.2.043364","volume":"2","author":"J Tangpanitanon","year":"2020","unstructured":"Tangpanitanon J, Thanasilp S, Dangniam N, Lemonde M-A, Angelakis D G (2020) Expressibility and trainability of parametrized analog quantum systems for machine learning applications. Phys Rev Res 2(4):043364","journal-title":"Phys Rev Res"},{"key":"103_CR73","doi-asserted-by":"crossref","unstructured":"Thanasilp S, et al. (2022) Exponential concentration and untrainability in quantum kernel methods, arxiv:https:\/\/arxiv.org\/abs\/2208.11060","DOI":"10.21203\/rs.3.rs-2296310\/v1"},{"key":"103_CR74","doi-asserted-by":"crossref","unstructured":"Thumwanit N, Lortararprasert C, Yano H, Raymond R (2021) Trainable discrete feature embeddings for variational quantum classifier. arXiv:https:\/\/arxiv.org\/abs\/2106.09415","DOI":"10.1109\/QCE52317.2021.00087"},{"key":"103_CR75","unstructured":"Verdon G, Marks J, Nanda S, Leichenauer S, Hidary J (2019) Quantum hamiltonian-based models and the variational quantum thermalizer algorithm. arXiv:https:\/\/arxiv.org\/abs\/1910.02071"},{"key":"103_CR76","unstructured":"Wang S, Czarnik P, Arrasmith A, Cerezo M, Cincio L, Coles P J (2021) Can error mitigation improve trainability of noisy variational quantum algorithms? arXiv:https:\/\/arxiv.org\/abs\/2109.01051"},{"issue":"1","key":"103_CR77","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-27045-6","volume":"12","author":"S Wang","year":"2021","unstructured":"Wang S, Fontana E, Cerezo M, Sharma K, Sone A, Cincio L, Coles P J (2021) Noise-induced barren plateaus in variational quantum algorithms. Nat Commun 12(1):1\u201311","journal-title":"Nat Commun"},{"issue":"21","key":"103_CR78","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1016\/j.scib.2021.06.023","volume":"66","author":"X Xu","year":"2021","unstructured":"Xu X, Sun J, Endo S, Li Y, Benjamin S C, Yuan X (2021) Variational algorithms for linear algebra. Sci Bull 66(21):2181\u20132188","journal-title":"Sci Bull"},{"key":"103_CR79","doi-asserted-by":"crossref","unstructured":"Zhao C, Gao X-S (2021) Analyzing the barren plateau phenomenon in training quantum neural network with the zx-calculus. arXiv:https:\/\/arxiv.org\/abs\/2102.01828","DOI":"10.22331\/q-2021-06-04-466"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-023-00103-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-023-00103-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-023-00103-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T11:25:43Z","timestamp":1729423543000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-023-00103-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,15]]},"references-count":79,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["103"],"URL":"https:\/\/doi.org\/10.1007\/s42484-023-00103-6","relation":{},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,15]]},"assertion":[{"value":"1 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interest"}}],"article-number":"21"}}