A rigorous and robust quantum speed-up in supervised machine learning
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Recently, several quantum machine learning algorithms have been proposed that may offer quantum speed-ups over their classical counterparts. Most of these algorithms are either heuristic or assume that data can be accessed quantum-mechanically, making it unclear whether a quantum advantage can be proven without resorting to strong assumptions. Here we construct a classification problem with which we can rigorously show that heuristic quantum kernel methods can provide an end-to-end quantum speed-up with only classical access to data. To prove the quantum speed-up, we construct a family of datasets and show that no classical learner can classify the data inverse-polynomially better than random guessing, assuming the widely believed hardness of the discrete logarithm problem. Furthermore, we construct a family of parameterized unitary circuits, which can be efficiently implemented on a fault-tolerant quantum computer, and use them to map the data samples to a quantum feature space and estimate the kernel entries. The resulting quantum classifier achieves high accuracy and is robust against additive errors in the kernel entries that arise from finite sampling statistics. Many quantum machine learning algorithms have been proposed, but it is typically unknown whether they would outperform classical methods on practical devices. A specially constructed algorithm shows that a formal quantum advantage is possible.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Note that this expressivity boost is not limited to neural networks and has been observed, for instance, for support vector machines.[222,228,229]”
From Quantum Computing for Molecular Biology** (2023) · cites this paper as [229]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A training algorithm for optimal margin classifiers
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130401 · Cited by 11,992
Polynomial-time algorithms for prime factorization and discrete logarithms on a quantum computer
Shor, P. W. (1997) · SIAM Journal on Computing · doi:10.1137/s0097539795293172 · Cited by 8,472
Kernel Methods for Pattern Analysis
Shawe-Taylor, J., & Cristianini, N. (2004) · Cambridge University Press eBooks · doi:10.1017/cbo9780511809682 · Cited by 6,587
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
Quantum Algorithm for Linear Systems of Equations
Harrow, A. W., Hassidim, A., & Lloyd, S. (2009) · Physical Review Letters · doi:10.1103/physrevlett.103.150502 · Cited by 3,325
Supervised learning with quantum-enhanced feature spaces
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019) · Nature · doi:10.1038/s41586-019-0980-2 · Cited by 2,572
Self-citationMachine learning and the physical sciences
Carleo, G., Cirac, I., Cranmer, K., Daudet, L., Schuld, M., Tishby, N., Vogt-Maranto, L., & Zdeborová, L. (2019) · Reviews of Modern Physics · doi:10.1103/revmodphys.91.045002 · Cited by 2,417
Quantum Support Vector Machine for Big Data Classification
Rebentrost, P., Mohseni, M., & Lloyd, S. (2014) · Physical Review Letters · doi:10.1103/physrevlett.113.130503 · Cited by 1,951
Quantum Machine Learning in Feature Hilbert Spaces
Schuld, M., & Killoran, N. (2019) · Physical Review Letters · doi:10.1103/physrevlett.122.040504 · Cited by 1,840
An Introduction to Computational Learning Theory
Kearns, M. J., & Vazirani, U. (1994) · doi:10.7551/mitpress/3897.001.0001 · Cited by 1,697
Research works printed but not linked: 5
- Brandão, F. G. S. L. et al. Quantum SDP solvers: large speed-ups, optimality and applications to quantum learning. In Proc. 46th International Colloquium on Automata, Languages and Programming, Leibniz International Proc. Informatics Vol. 132 (eds Baier, C. et al.) 27:1–27:14 (Schloss Dagstuhl—Leibniz-Zentrum für Informatik, 2019); http://drops.dagstuhl.de/opus/volltexte/2019/10603
- Vapnik, V. The Nature of Statistical Learning Theory (Springer Science & Business Media, 2013).
- Kearns, M. J. The Computational Complexity of Machine Learning (MIT Press, 1990).
- Harrow, A. W. Small quantum computers and large classical data sets. Preprint at https://arxiv.org/pdf/2004.00026.pdf (2020). · arXiv
- Li, Y. & Benjamin, S. C. Efficient variational quantum simulator incorporating active error minimization. Phys. Rev. X 7, 021050 (2017).
Cited by
Power of data in quantum machine learning
Huang, H.-Y., Broughton, M., Mohseni, M., Babbush, R., Boixo, S., Neven, H., & McClean, J. R. (2021) · Nature Communications · doi:10.1038/s41467-021-22539-9 · Cited by 896
Challenges and opportunities in quantum machine learning
Cerezo, M., Verdon, G., Huang, H.-Y., Cincio, L., & Coles, P. J. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00311-3 · Cited by 689
“[27] Yunchao Liu, Srinivasan Arunachalam, and Kristan Temme, “A rigorous and robust quantum speed-up in supervised machine learning,” Nature Physics , 1–5 (2021).”
BackgroundGeneralization in quantum machine learning from few training data
Caro, M. C., Huang, H.-Y., Cerezo, M., Sharma, K., Sornborger, A., Cincio, L., & Coles, P. J. (2022) · Nature Communications · doi:10.1038/s41467-022-32550-3 · Cited by 476
The future of quantum computing with superconducting qubits
Bravyi, S., Dial, O., Gambetta, J. M., Gil, D., & Nazario, Z. (2022) · Journal of Applied Physics · doi:10.1063/5.0082975 · Cited by 334
“Quantum kernel methods have also been found that lead to provable speedups 101 and expand to a class of kernels for data with group structure 102 .”
MethodA Survey of Important Issues in Quantum Computing and Communications
Yang, Z., Zolanvari, M., & Jain, R. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3254481 · Cited by 251
“For example, heuristic quantum kernel methods have been applied to a classification problem with only classical access to data [291].”
Method
Metadata
- Authors
- Liu, Y., Arunachalam, S., & Temme, K.
- Affiliations
- IBM (United States) (US)
- Corresponding author
- Temme, Kristan
- Venue
- Nature Physics
- Published
- 2021-07-12
- Volume
- 17
- Issue
- 9
- Pages
- 1013-1017
- ISSN
- 1745-2473 (ISSN-L)
- 1745-2481
- OpenAlex
- W3090365491
- Cited by
- 649
- References
- 41
- Citations by year
- 2026: 141 · 2025: 151 · 2024: 140 · 2023: 115 · 2022: 68 · 2021: 31
- FWCI
- 29.81
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Nature Physics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. Department of Energy
- Army Research Office (W911NF-20, W911NF-20-1-0014)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum Information and Cryptography
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum many-body systems
- Keywords
- quantum machine learning, quantum advantage, quantum kernel methods, supervised classification, discrete logarithm problem, hardness of learning, variational quantum circuits, kernel estimation, fault-tolerant quantum computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A rigorous and robust quantum speed-up in supervised machine learning. https://app.cochat.ai/papers/10.1038/s41567-021-01287-z
- The paper
- Liu, Y., Arunachalam, S., & Temme, K. (2021). A rigorous and robust quantum speed-up in supervised machine learning. Nature Physics. https://doi.org/10.1038/s41567-021-01287-z
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.