{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T10:49:41Z","timestamp":1786618181195,"version":"3.56.0"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"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":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Quantum extreme learning machines (QELMs) have emerged as a promising framework for quantum machine learning. Their appeal lies in the rich feature map induced by the dynamics of a quantum substrate\u2014the quantum reservoir\u2014and the efficient post-measurement training via linear regression. Here, we study the expressivity of QELMs by decomposing the prediction of QELMs into a Fourier series. We show that the achievable Fourier frequencies are determined by the data encoding scheme, while Fourier coefficients depend on both the reservoir and the measurement. Notably, the expressivity of QELMs is fundamentally limited by the number of Fourier frequencies and the number of observables, while the complexity of the prediction hinges on the reservoir. As a cautionary note on scalability, we identify four sources that can lead to the exponential concentration of the observables as the system size grows (randomness, hardware noise, entanglement, and global measurements) and show how this can turn QELMs into useless input-agnostic oracles. In particular, our result on the reservoir-induced concentration strongly indicates that quantum reservoirs drawn from a highly random ensemble make QELM models unscalable. Our analysis elucidates the potential and fundamental limitations of QELMs and lays the groundwork for systematically exploring quantum reservoir systems for other machine learning tasks.<\/jats:p>","DOI":"10.1007\/s42484-025-00239-7","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T12:42:16Z","timestamp":1739450536000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["On fundamental aspects of quantum extreme learning machines"],"prefix":"10.1007","volume":"7","author":[{"given":"Weijie","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Facelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehrad","family":"Sahebi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Owen","family":"Agnel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thiparat","family":"Chotibut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Supanut","family":"Thanasilp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zo\u00eb","family":"Holmes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"key":"239_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed O, Tennie F, Magri L (2024) Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics. https:\/\/doi.org\/10.48550\/arXiv.2409.01394. arXiv:2409.01394","DOI":"10.48550\/arXiv.2409.01394"},{"key":"239_CR2","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 PJ (2021) Effect of barren plateaus on gradient-free optimization. Quantum 5:558","journal-title":"Quantum"},{"key":"239_CR3","doi-asserted-by":"publisher","first-page":"045015","DOI":"10.1088\/2058-9565\/ac7d06","volume":"7","author":"A Arrasmith","year":"2022","unstructured":"Arrasmith A, Holmes Z, Cerezo M, Coles PJ (2022) Equivalence of quantum barren plateaus to cost concentration and narrow gorges. Quantum Sci Technol 7:045015","journal-title":"Quantum Sci Technol"},{"key":"239_CR4","doi-asserted-by":"publisher","unstructured":"Bartheand A, P\u00e9rez-Salinas A (2023) Gradients and frequency profiles of quantum re-uploading models. https:\/\/doi.org\/10.48550\/arXiv.2311.10822. arXiv:2311.10822","DOI":"10.48550\/arXiv.2311.10822"},{"key":"239_CR5","doi-asserted-by":"publisher","first-page":"030201","DOI":"10.1103\/PRXQuantum.3.030201","volume":"3","author":"E Bianchi","year":"2022","unstructured":"Bianchi E, Hackl L, Kieburg M, Rigol M, Vidmar L (2022) Volume-law entanglement entropy of typical pure quantum states. PRX Quantum 3:030201","journal-title":"PRX Quantum"},{"key":"239_CR6","doi-asserted-by":"publisher","first-page":"582","DOI":"10.22331\/q-2021-11-17-582","volume":"5","author":"MC Caro","year":"2021","unstructured":"Caro MC, Gil-Fuster E, Meyer JJ, Eisert J, Sweke R (2021) Encoding-dependent generalization bounds for parametrized quantum circuits. Quantum 5:582","journal-title":"Quantum"},{"key":"239_CR7","doi-asserted-by":"publisher","first-page":"035006","DOI":"10.1088\/2058-9565\/abf51a","volume":"6","author":"M Cerezo","year":"2021","unstructured":"Cerezo M, Coles PJ (2021) Higher order derivatives of quantum neural networks with barren plateaus. Quantum Sci Technol 6:035006","journal-title":"Quantum Sci Technol"},{"key":"239_CR8","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 PJ (2021) Cost function dependent barren plateaus in shallow parametrized quantum circuits. Nat Commun 12:1","journal-title":"Nat Commun"},{"key":"239_CR9","doi-asserted-by":"publisher","unstructured":"Cerezo M, Larocca M, Garc\u00eda-Mart\u00edn D, Diaz N, Braccia P, Fontana E, Rudolph MS, Bermejo P, Ijaz A, Thanasilp S et\u00a0al (2023) Does provable absence of barren plateaus imply classical simulability? Or, why we need to rethink variational quantum computing. https:\/\/doi.org\/10.48550\/arXiv.2312.09121. arXiv:2312.09121","DOI":"10.48550\/arXiv.2312.09121"},{"key":"239_CR10","doi-asserted-by":"publisher","unstructured":"Chang SY, Thanasilp S, Saux BL, Vallecorsa S, Grossi M (2024) Latent style-based quantum GAN for high-quality image generation. https:\/\/doi.org\/10.48550\/arXiv.2406.02668. arXiv:2406.02668","DOI":"10.48550\/arXiv.2406.02668"},{"key":"239_CR11","doi-asserted-by":"publisher","unstructured":"\u010cindrak S, Jaurigue L, L\u00fcdge K (2024) Krylov expressivity in quantum reservoir computing and quantum extreme learning. https:\/\/doi.org\/10.48550\/arXiv.2409.12079. arXiv:2409.12079","DOI":"10.48550\/arXiv.2409.12079"},{"key":"239_CR12","doi-asserted-by":"crossref","unstructured":"De\u00a0Chazal P, Tapson J, Van\u00a0Schaik A (2015) A comparison of extreme learning machines and back-propagation trained feed-forward networks processing the mnist database. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) organization. IEEE, pp 2165\u20132168","DOI":"10.1109\/ICASSP.2015.7178354"},{"key":"239_CR13","doi-asserted-by":"publisher","unstructured":"De\u00a0Lorenzis A, Casado M, Estarellas M, Gullo NL, Lux T, Plastina F, Riera A, Settino J (2024) Harnessing quantum extreme learning machines for image classification. https:\/\/doi.org\/10.48550\/arXiv.2409.00998. arXiv preprint arXiv:2409.00998","DOI":"10.48550\/arXiv.2409.00998"},{"key":"239_CR14","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s10462-013-9405-z","volume":"44","author":"S Ding","year":"2015","unstructured":"Ding S, Zhao H, Zhang Y, Xu X, Nie R (2015) Extreme learning machine: algorithm, theory and applications. Artif Intell Rev 44:103","journal-title":"Artif Intell Rev"},{"key":"239_CR15","doi-asserted-by":"publisher","unstructured":"Domingo L, Grande M, Carlo G, Borondo F, Borondo J (2023) Optimal quantum reservoir computing for market forecasting: an application to fight food price crises. https:\/\/doi.org\/10.48550\/arXiv.2409.01394. arXiv:2401.03347","DOI":"10.48550\/arXiv.2409.01394"},{"key":"239_CR16","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1103\/RevModPhys.82.277","volume":"82","author":"J Eisert","year":"2010","unstructured":"Eisert J, Cramer M, Plenio MB (2010) Colloquium: area laws for the entanglement entropy. Rev Mod Phys 82:277","journal-title":"Rev Mod Phys"},{"key":"239_CR17","unstructured":"Fontana E, Herman D, Chakrabarti S, Kumar N, Yalovetzky R, Heredge J, Hari\u00a0Sureshbabu S, Pistoia M (2023) The adjoint is all you need: characterizing barren plateaus in quantum ans\u00e4tze. arXiv:2309.07902"},{"key":"239_CR18","doi-asserted-by":"publisher","unstructured":"Fry D, Deshmukh A, Chen SY-C, Rastunkov V, Markov V (2023) Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction. https:\/\/doi.org\/10.48550\/arXiv.2303.05488. arXiv:2303.05488","DOI":"10.48550\/arXiv.2303.05488"},{"key":"239_CR19","doi-asserted-by":"publisher","unstructured":"Fuchs FG, Stasik AJ, Miao S, Kulseng OT, Bassa RP (2024) Quantum reservoir computing using the stabilizer formalism for encoding classical data. https:\/\/doi.org\/10.48550\/arXiv.2407.00445. arXiv:2407.00445","DOI":"10.48550\/arXiv.2407.00445"},{"key":"239_CR20","doi-asserted-by":"publisher","first-page":"024030","DOI":"10.1103\/PhysRevApplied.8.024030","volume":"8","author":"K Fujiiand","year":"2017","unstructured":"Fujiiand K, Nakajima K (2017) Harnessing disordered-ensemble quantum dynamics for machine learning. Phys Rev Appl 8:024030","journal-title":"Phys Rev Appl"},{"key":"239_CR21","doi-asserted-by":"crossref","unstructured":"Fujiiand K, Nakajima K (2021) Quantum reservoir computing: a reservoir approach toward quantum machine learning on near-term quantum devices. Reservoir Computing: Theory, Physical Implementations, and Applications, p 423","DOI":"10.1007\/978-981-13-1687-6_18"},{"key":"239_CR22","doi-asserted-by":"publisher","unstructured":"Gan BY, Leykam D, Thanasilp S (2023) A unified framework for trace-induced quantum kernels. https:\/\/doi.org\/10.48550\/arXiv.2311.13552. arXiv:2311.13552","DOI":"10.48550\/arXiv.2311.13552"},{"key":"239_CR23","unstructured":"Garc\u00eda-Mart\u00edn D, Larocca M, Cerezo M (2023) Deep quantum neural networks form Gaussian processes. arXiv:2305.09957"},{"key":"239_CR24","doi-asserted-by":"publisher","first-page":"035302","DOI":"10.1103\/PhysRevE.105.035302","volume":"105","author":"MR Geller","year":"2022","unstructured":"Geller MR, Arrasmith A, Holmes Z, Yan B, Coles PJ, Sornborger A (2022) Quantum simulation of operator spreading in the chaotic Ising model. Phys Rev E 105:035302","journal-title":"Phys Rev E"},{"key":"239_CR25","doi-asserted-by":"crossref","unstructured":"Ghosh S, Opala A, Matuszewski M, Paterek T, Liew TCH (2019a) Quantum reservoir processing. Npj Quantum Inf 5:35","DOI":"10.1038\/s41534-019-0149-8"},{"key":"239_CR26","doi-asserted-by":"crossref","unstructured":"Ghosh S, Paterek T, Liew TCH (2019b) Quantum neuromorphic platform for quantum state preparation. Phys Rev Lett 123:260404","DOI":"10.1103\/PhysRevLett.123.260404"},{"key":"239_CR27","doi-asserted-by":"publisher","unstructured":"Gonon L, Jacquier A (2023) Universal approximation theorem and error bounds for quantum neural networks and quantum reservoirs. https:\/\/doi.org\/10.48550\/arXiv.2307.12904. arXiv:2307.12904","DOI":"10.48550\/arXiv.2307.12904"},{"key":"239_CR28","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press"},{"issue":"9","key":"239_CR29","doi-asserted-by":"publisher","first-page":"090506","DOI":"10.1103\/PhysRevLett.127.090506","volume":"127","author":"T Goto","year":"2021","unstructured":"Goto T, Tran QH, Nakajima K (2021) Universal approximation property of quantum machine learning models in quantum-enhanced feature spaces. Phys Rev Lett 127(9):090506","journal-title":"Phys Rev Lett"},{"key":"239_CR30","doi-asserted-by":"publisher","first-page":"010313","DOI":"10.1103\/PRXQuantum.3.010313","volume":"3","author":"Z Holmes","year":"2022","unstructured":"Holmes Z, Sharma K, Cerezo M, Coles PJ (2022) Connecting ansatz expressibility to gradient magnitudes and barren plateaus. PRX Quantum 3:010313","journal-title":"PRX Quantum"},{"key":"239_CR31","doi-asserted-by":"publisher","unstructured":"Holmes Z, Arrasmith A, Yan B, Coles PJ, Albrecht A, Sornborger AT (2021) Barren plateaus preclude learning scramblers. Phys Rev Lett 126(19):190501. https:\/\/doi.org\/10.1103\/PhysRevLett.126.190501","DOI":"10.1103\/PhysRevLett.126.190501"},{"key":"239_CR32","doi-asserted-by":"crossref","unstructured":"Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541). IEEE, pp 985\u2013990","DOI":"10.1109\/IJCNN.2004.1380068"},{"issue":"1\u20133","key":"239_CR33","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1\u20133):489","journal-title":"Neurocomputing"},{"issue":"2","key":"239_CR34","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","volume":"42","author":"G-B Huang","year":"2011","unstructured":"Huang G-B, Zhou H, Ding X, Zhang R (2011) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(2):513","journal-title":"IEEE Trans Syst Man Cybern Part B (Cybernetics)"},{"key":"239_CR35","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.neunet.2014.10.001","volume":"61","author":"G Huang","year":"2015","unstructured":"Huang G, Huang G-B, Song S, You K (2015) Trends in extreme learning machines: a review. Neural Netw 61:32","journal-title":"Neural Netw"},{"issue":"10","key":"239_CR36","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1038\/s41567-020-0932-7","volume":"16","author":"HY Huang","year":"2020","unstructured":"Huang HY, Kueng R, Preskill J (2020) Predicting many properties of a quantum system from very few measurements. Nat Phys 16(10):1050","journal-title":"Nat Phys"},{"key":"239_CR37","doi-asserted-by":"crossref","unstructured":"Innocenti L, Lorenzo S, Palmisano I, Albarelli F, Ferraro A, Paternostro M, Palma GM (2023a) Shadow tomography on general measurement frames. PRX Quantum 4(4):040328","DOI":"10.1103\/PRXQuantum.4.040328"},{"key":"239_CR38","doi-asserted-by":"crossref","unstructured":"Innocenti L, Lorenzo S, Palmisano I, Ferraro A, Paternostro M, Palma GM (2023b) Potential and limitations of quantum extreme learning machines. Commun Phys 6(1):118","DOI":"10.1038\/s42005-023-01233-w"},{"key":"239_CR39","doi-asserted-by":"publisher","unstructured":"Kornja\u010da M, Hu HY, Zhao C, Wurtz J, Weinberg P, Hamdan M, Zhdanov A, Cantu SH, Zhou H, Bravo RA et al (2024) Large-scale quantum reservoir learning with an analog quantum computer. https:\/\/doi.org\/10.48550\/arXiv.2407.02553. arXiv:2407.02553","DOI":"10.48550\/arXiv.2407.02553"},{"key":"239_CR40","doi-asserted-by":"publisher","first-page":"023057","DOI":"10.1103\/PhysRevResearch.5.023057","volume":"5","author":"T Kubota","year":"2023","unstructured":"Kubota T, Suzuki Y, Kobayashi S, Tran QH, Yamamoto N, Nakajima K (2023) Temporal information processing induced by quantum noise. Phys Rev Res 5:023057","journal-title":"Phys Rev Res"},{"issue":"1","key":"239_CR41","doi-asserted-by":"publisher","first-page":"14687","DOI":"10.1038\/s41598-020-71673-9","volume":"10","author":"A Kutvonen","year":"2020","unstructured":"Kutvonen A, Fujii K, Sagawa T (2020) Optimizing a quantum reservoir computer for time series prediction. Sci Rep 10(1):14687","journal-title":"Sci Rep"},{"key":"239_CR42","unstructured":"Landman J, Thabet S, Dalyac C, Mhiri H, Kashefi E (2022) Classically approximating variational quantum machine learning with random Fourier features. arXiv:2210.13200"},{"key":"239_CR43","doi-asserted-by":"publisher","unstructured":"Larocca M, Thanasilp S, Wang S, Sharma K, Biamonte J, Coles PJ, Cincio L, McClean JR, Holmes Z, Cerezo M (2024) A review of barren plateaus in variational quantum computing. https:\/\/doi.org\/10.48550\/arXiv.2405.00781. arXiv:2405.00781","DOI":"10.48550\/arXiv.2405.00781"},{"key":"239_CR44","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","DOI":"10.1038\/s41567-021-01287-z"},{"issue":"4","key":"239_CR45","first-page":"040316","volume":"2","author":"CO Marrero","year":"2021","unstructured":"Marrero CO, Kieferov\u00e1 M, Wiebe N (2021) Entanglement-induced barren plateaus. PRX. Quantum 2(4):040316","journal-title":"Quantum"},{"key":"239_CR46","doi-asserted-by":"publisher","first-page":"100502","DOI":"10.1103\/PhysRevLett.127.100502","volume":"127","author":"R Mart\u00ednez-Pe\u00f1a","year":"2021","unstructured":"Mart\u00ednez-Pe\u00f1a R, Giorgi GL, Nokkala J, Soriano MC, Zambrini R (2021) Dynamical phase transitions in quantum reservoir computing. Phys Rev Lett 127:100502","journal-title":"Phys Rev Lett"},{"key":"239_CR47","doi-asserted-by":"publisher","unstructured":"Mart\u00ednez-Pe\u00f1a R, Ortega JP (2024) Input-dependence in quantum reservoir computing. https:\/\/doi.org\/10.48550\/arXiv.2412.08322. arXiv:2412.08322","DOI":"10.48550\/arXiv.2412.08322"},{"issue":"1","key":"239_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07090-4","volume":"9","author":"JR McClean","year":"2018","unstructured":"McClean JR, Boixo S, Smelyanskiy VN, Babbush R, Neven H (2018) Barren plateaus in quantum neural network training landscapes. Nat Commun 9(1):1","journal-title":"Nat Commun"},{"key":"239_CR49","doi-asserted-by":"publisher","unstructured":"Mhiri H, Monbroussou L, Gonzalez MH, Thabet S, Landman J, Kashefi E (2024) Constrained and vanishing expressivity of quantum Fourier models. https:\/\/doi.org\/10.48550\/arXiv.2403.09417. arXiv:2403.09417","DOI":"10.48550\/arXiv.2403.09417"},{"key":"239_CR50","doi-asserted-by":"crossref","unstructured":"Mujal P, Mart\u00ed nez-Pe\u00f1a R, Nokkala J, Garc\u00eda-Beni J, Giorgi GL, Soriano MC, Zambrini R (2021) Opportunities in quantum reservoir computing and extreme learning machines. Adv Quantum Technol 4(8):2100027","DOI":"10.1002\/qute.202100027"},{"key":"239_CR51","doi-asserted-by":"publisher","unstructured":"Muqeet A, Sartaj H, Arreieta A, Ali S, Arcaini P, Arratibel M, Gj\u00f8by JM, Veeraragavan NR et al (2024) Assessing quantum extreme learning machines for software testing in practice. https:\/\/doi.org\/10.48550\/arXiv.2410.15494. arXiv:2410.15494","DOI":"10.48550\/arXiv.2410.15494"},{"key":"239_CR52","doi-asserted-by":"publisher","first-page":"034021","DOI":"10.1103\/PhysRevApplied.11.034021","volume":"11","author":"K Nakajima","year":"2019","unstructured":"Nakajima K, Fujii K, Negoro M, Mitarai K, Kitagawa M (2019) Boosting computational power through spatial multiplexing in quantum reservoir computing. Phys Rev Appl 11:034021","journal-title":"Phys Rev Appl"},{"key":"239_CR53","doi-asserted-by":"crossref","unstructured":"Negoro M, Mitarai K, Nakajima K, Fujii K (2021) Toward NMR quantum reservoir computing. Reservoir computing: theory, physical implementations, and applications, pp 451\u2013458","DOI":"10.1007\/978-981-13-1687-6_19"},{"key":"239_CR54","doi-asserted-by":"publisher","unstructured":"Nerenberg S, Neill O, Marcucci G, Faccio D (2024) Photon number-resolving quantum reservoir computing. https:\/\/doi.org\/10.48550\/arXiv.2402.06339. arXiv:2402.06339","DOI":"10.48550\/arXiv.2402.06339"},{"key":"239_CR55","doi-asserted-by":"crossref","unstructured":"Odlyzko A (2000) Discrete logarithms: the past and the future. Towards a quarter-century of public key cryptography: a special issue of designs, codes and cryptography an international journal volume 19, No 2\/3 (2000) pp 59","DOI":"10.1007\/978-1-4757-6856-5_3"},{"key":"239_CR56","doi-asserted-by":"crossref","unstructured":"Palacios A, Mart\u00ednez-Pe\u00f1a R, Soriano MC, Giorgi GL, Zambrini R (2024) Role of coherence in many-body quantum reservoir computing. Commun Phys 7(1):369","DOI":"10.1038\/s42005-024-01859-4"},{"key":"239_CR57","doi-asserted-by":"publisher","unstructured":"Puig R, Drudis M, Thanasilp S, Holmes Z (2024) Variational quantum simulation: a case study for understanding warm starts. https:\/\/doi.org\/10.48550\/arXiv.2404.10044. arXiv:2404.10044","DOI":"10.48550\/arXiv.2404.10044"},{"key":"239_CR58","doi-asserted-by":"crossref","unstructured":"Ragone M, Bakalov BN, Sauvage F, Kemper F, Marrero CO, Larocca M, Cerezo M (2023) A unified theory of barren plateaus for deep parametrized quantum circuits. arXiv:2309.09342","DOI":"10.1038\/s41467-024-49909-3"},{"key":"239_CR59","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/JHEP04(2017)121","volume":"4","author":"DA Roberts","year":"2017","unstructured":"Roberts DA, Yoshida B (2017) Chaos and complexity by design. J High Energy Phys 4:121","journal-title":"J High Energy Phys"},{"key":"239_CR60","doi-asserted-by":"crossref","unstructured":"Rudolph MS, Lerch S, Thanasilp S, Kiss O, Vallecorsa S, Grossi M, Holmes Z (2023) Trainability barriers and opportunities in quantum generative modeling. arXiv:2305.02881","DOI":"10.1038\/s41534-024-00902-0"},{"key":"239_CR61","unstructured":"Sainz de\u00a0la Maza\u00a0Gamboa U (2022) Quantum extreme learning machine for classification tasks. PhD thesis, Universidad del Pais Vasco"},{"issue":"6","key":"239_CR62","doi-asserted-by":"publisher","first-page":"064044","DOI":"10.1103\/PhysRevApplied.17.064044","volume":"17","author":"A Sakurai","year":"2022","unstructured":"Sakurai A, Estarellas MP, Munro WJ, Nemoto K (2022) Quantum extreme reservoir computation utilizing scale-free networks. Phys Rev Appl 17(6):064044","journal-title":"Phys Rev Appl"},{"issue":"10","key":"239_CR63","doi-asserted-by":"publisher","first-page":"100803","DOI":"10.1103\/PhysRevLett.131.100803","volume":"131","author":"FJ Schreiber","year":"2023","unstructured":"Schreiber FJ, Eisert J, Meyer JJ (2023) Classical surrogates for quantum learning models. Phys Rev Lett 131(10):100803","journal-title":"Phys Rev Lett"},{"issue":"3","key":"239_CR64","doi-asserted-by":"publisher","first-page":"032430","DOI":"10.1103\/PhysRevA.103.032430","volume":"103","author":"M Schuld","year":"2021","unstructured":"Schuld M, Sweke R, Meyer JJ (2021) Effect of data encoding on the expressive power of variational quantum-machine-learning models. Phys Rev A 103(3):032430","journal-title":"Phys Rev A"},{"issue":"1","key":"239_CR65","doi-asserted-by":"publisher","first-page":"7490","DOI":"10.1038\/s41467-024-51161-8","volume":"15","author":"A Senanian","year":"2024","unstructured":"Senanian A, Prabhu S, Kremenetski V, Roy S, Cao Y, Kline J, Onodera T, Wright LG, Wu X, Fatemi V et al (2024) Microwave signal processing using an analog quantum reservoir computer. Nat Commun 15(1):7490","journal-title":"Nat Commun"},{"issue":"18","key":"239_CR66","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 PJ (2022) Trainability of dissipative perceptron-based quantum neural networks. Phys Rev Lett 128(18):180505","journal-title":"Phys Rev Lett"},{"issue":"1","key":"239_CR67","doi-asserted-by":"publisher","first-page":"012422","DOI":"10.1103\/PhysRevA.107.012422","volume":"107","author":"S Shin","year":"2023","unstructured":"Shin S, Teo Y, Jeong H (2023) Exponential data encoding for quantum supervised learning. Phys Rev A 107(1):012422","journal-title":"Phys Rev A"},{"key":"239_CR68","doi-asserted-by":"crossref","unstructured":"Shor PW (1994) Algorithms for quantum computation: discrete logarithms and factoring. In: Proceedings 35th annual symposium on foundations of computer science. IEEE, pp 124\u2013134","DOI":"10.1109\/SFCS.1994.365700"},{"issue":"2","key":"239_CR69","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s42484-024-00188-7","volume":"6","author":"A Sornsaeng","year":"2024","unstructured":"Sornsaeng A, Dangniam N, Chotibut T (2024) Quantum next generation reservoir computing: an efficient quantum algorithm for forecasting quantum dynamics. Quantum Mach Intell 6(2):57","journal-title":"Quantum Mach Intell"},{"issue":"16","key":"239_CR70","doi-asserted-by":"publisher","first-page":"160802","DOI":"10.1103\/PhysRevLett.132.160802","volume":"132","author":"A Suprano","year":"2024","unstructured":"Suprano A, Zia D, Innocenti L, Lorenzo S, Cimini V, Giordani T, Palmisano I, Polino E, Spagnolo N, Sciarrino F et al (2024) Experimental property reconstruction in a photonic quantum extreme learning machine. Phys Rev Lett 132(16):160802","journal-title":"Phys Rev Lett"},{"key":"239_CR71","doi-asserted-by":"publisher","unstructured":"Suprano A, Zia D, Innocenti L, Lorenzo S, Cimini V, Giordani T, Palmisano I, Polino E, Spagnolo N, Sciarrino F et al (2023) Experimental property-reconstruction in a photonic quantum extreme learning machine. https:\/\/doi.org\/10.48550\/arXiv.2308.04543. arXiv:2308.04543","DOI":"10.48550\/arXiv.2308.04543"},{"issue":"1","key":"239_CR72","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1038\/s41598-022-05061-w","volume":"12","author":"Y Suzuki","year":"2022","unstructured":"Suzuki Y, Gao Q, Pradel KC, Yasuoka K, Yamamoto N (2022) Natural quantum reservoir computing for temporal information processing. Sci Rep 12(1):1353","journal-title":"Sci Rep"},{"key":"239_CR73","unstructured":"Sweke R, Recio E, Jerbi S, Gil-Fuster E, Fuller B, Eisert J, Meyer JJ (2023) Potential and limitations of random Fourier features for dequantizing quantum machine learning. arXiv:2309.11647"},{"issue":"1","key":"239_CR74","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1038\/s41467-024-49287-w","volume":"15","author":"S Thanasilp","year":"2024","unstructured":"Thanasilp S, Wang S, Cerezo M, Holmes Z (2024) Exponential concentration in quantum kernel methods. Nat Commun 15(1):5200","journal-title":"Nat Commun"},{"key":"239_CR75","doi-asserted-by":"publisher","DOI":"10.1007\/b13794","volume-title":"Introduction to nonparametric estimation","author":"AB Tsybakov","year":"2009","unstructured":"Tsybakov AB (2009) Introduction to nonparametric estimation. Springer"},{"issue":"24","key":"239_CR76","doi-asserted-by":"publisher","first-page":"245301","DOI":"10.1088\/1751-8121\/abfac7","volume":"54","author":"A Uvarov","year":"2021","unstructured":"Uvarov A, Biamonte JD (2021) On barren plateaus and cost function locality in variational quantum algorithms. J Phys A Math Theor 54(24):245301","journal-title":"J Phys A Math Theor"},{"issue":"2","key":"239_CR77","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s42484-024-00176-x","volume":"6","author":"S Varsamopoulos","year":"2024","unstructured":"Varsamopoulos S, Philip E, Elfving VE, van Vlijmen HW, Menon S, Vos A, Dyubankova N, Torfs B, Rowe A (2024) Quantum extremal learning. Quantum Mach Intell 6(2):42","journal-title":"Quantum Mach Intell"},{"key":"239_CR78","doi-asserted-by":"publisher","unstructured":"Vetrano M, Monaco GL, Innocenti L, Lorenzo S, Palma GM (2024) State estimation with quantum extreme learning machines beyond the scrambling time. https:\/\/doi.org\/10.48550\/arXiv.2409.06782. arXiv:2409.06782","DOI":"10.48550\/arXiv.2409.06782"},{"key":"239_CR79","doi-asserted-by":"crossref","unstructured":"Wang S, Fontana E, Cerezo M, Sharma K, Sone A, Cincio L, Coles PJ (2021) Noise-induced barren plateaus in variational quantum algorithms. Nat Commun 12(1):1","DOI":"10.1038\/s41467-021-27045-6"},{"key":"239_CR80","doi-asserted-by":"crossref","unstructured":"Wang Y, Lin K-Y, Cheng S, Li L (2022) Variational quantum extreme learning machine. Neurocomputing 512:83","DOI":"10.1016\/j.neucom.2022.09.068"},{"key":"239_CR81","doi-asserted-by":"crossref","unstructured":"Wang J, Lu S, Wang S-H, Zhang Y-D (2022) A review on extreme learning machine. Multimed Tools Appl 81(29):41611","DOI":"10.1007\/s11042-021-11007-7"},{"key":"239_CR82","doi-asserted-by":"publisher","unstructured":"Wudarski F, O\u2019Connor D, Geaney S, Asanjan AA, Wilson M, Strbac E, Lott PA, Venturelli D (2023) Hybrid quantum-classical reservoir computing for simulating chaotic systems. https:\/\/doi.org\/10.48550\/arxiv.2311.14105. arXiv:2311.14105","DOI":"10.48550\/arxiv.2311.14105"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00239-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-025-00239-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00239-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T14:41:34Z","timestamp":1750948894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-025-00239-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":82,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["239"],"URL":"https:\/\/doi.org\/10.1007\/s42484-025-00239-7","relation":{},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]},"assertion":[{"value":"12 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2025","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":"Conflict of interest"}}],"article-number":"20"}}