CoChat

The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.

Power of data in quantum machine learning

Open access
Huang, Hsin-Yuan, Broughton, Michael, Mohseni, Masoud, Babbush, Ryan, Boixo, Sergio, Neven, Hartmut, McClean, Jarrod R. · 2021 · Nature Communications

Abstract

The use of quantum computing for machine learning is among the most exciting prospective applications of quantum technologies. However, machine learning tasks where data is provided can be considerably different than commonly studied computational tasks. In this work, we show that some problems that are classically hard to compute can be easily predicted by classical machines learning from data. Using rigorous prediction error bounds as a foundation, we develop a methodology for assessing potential quantum advantage in learning tasks. The bounds are tight asymptotically and empirically predictive for a wide range of learning models. These constructions explain numerical results showing that with the help of data, classical machine learning models can be competitive with quantum models even if they are tailored to quantum problems. We then propose a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime. For near-term implementations, we demonstrate a significant prediction advantage over some classical models on engineered data sets designed to demonstrate a maximal quantum advantage in one of the largest numerical tests for gate-based quantum machine learning to date, up to 30 qubits.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-021-22539-9

Cites

69 of 69 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Illustration of the relation between complexity classes and a flowchart for understanding and prescreening potential quantum advantage. a We cartoon the separation between problem complexities that are created by the addition of data to a problem. Classical algorithms that can learn from data define a complexity class that can solve problems beyond classical computation (BPP), but it is still expected that quantum computation can efficiently solve problems that classical ML algorithms with data cannot. A rigorous definition and proof for the separation between classical algorithms that can learn from data and BPP/BQP is given in Supplementary Section 2. b The flowchart we develop for understanding the potential for quantum prediction advantage. N samples of data from a potentially infinite depth QNN made with encoding and function circuits Uenc and UQNN are provided as input along with quantum and classical methods with associated kernels. Tests are given as functions of N to emphasize the role of data in the possibility of a prediction advantage. One can first evaluate a geometric quantity gCQ that measures the possibility of an advantageous quantum/classical prediction separation without yet considering the actual function to learn. We show how one can efficiently construct an adversarial function that saturates this limit if the test is passed, otherwise the classical approach is guaranteed to match performance for any function of the data. To subsequently consider the actual function provided, a label/function-specific test may be run using the model complexities sC and sQ. If one specifically uses the quantum kernel (QK) method, the red dashed arrows can evaluate if all possible choices of UQNN lead to an easy classical function for the chosen encoding of the data.
Fig. 1 Illustration of the relation between complexity classes and a flowchart for understanding and prescreening potential quantum advantage. a We cartoon the separation between problem complexities that are created by the addition of data to a problem. Classical algorithms that can learn from data define a complexity class that can solve problems beyond classical computation (BPP), but it is still expected that quantum computation can efficiently solve problems that classical ML algorithms with data cannot. A rigorous definition and proof for the separation between classical algorithms that can learn from data and BPP/BQP is given in Supplementary Section 2. b The flowchart we develop for understanding the potential for quantum prediction advantage. N samples of data from a potentially infinite depth QNN made with encoding and function circuits Uenc and UQNN are provided as input along with quantum and classical methods with associated kernels. Tests are given as functions of N to emphasize the role of data in the possibility of a prediction advantage. One can first evaluate a geometric quantity gCQ that measures the possibility of an advantageous quantum/classical prediction separation without yet considering the actual function to learn. We show how one can efficiently construct an adversarial function that saturates this limit if the test is passed, otherwise the classical approach is guaranteed to match performance for any function of the data. To subsequently consider the actual function provided, a label/function-specific test may be run using the model complexities sC and sQ. If one specifically uses the quantum kernel (QK) method, the red dashed arrows can evaluate if all possible choices of UQNN lead to an easy classical function for the chosen encoding of the data.CC BY · PubMed Central
Fig. 2 Cartoon of the geometry (kernel function) defined by classical and quantum ML models. The letters A, B, ... represent data points {xi} in different spaces with arrows representing the similarity measure (kernel function) between data. The geometric difference g is a difference between similarity measures (arrows) in different ML models and d is an effective dimension of the dataset in the quantum Hilbert space.
Fig. 2 Cartoon of the geometry (kernel function) defined by classical and quantum ML models. The letters A, B, ... represent data points {xi} in different spaces with arrows representing the similarity measure (kernel function) between data. The geometric difference g is a difference between similarity measures (arrows) in different ML models and d is an effective dimension of the dataset in the quantum Hilbert space.CC BY · PubMed Central
Fig. 3 Relation between dimension d, geometric difference g, and prediction performance. The shaded regions are the standard deviation over 10 independent runs and n is the number of qubits in the quantum encoding and dimension of the input for the classical encoding. a The approximate dimension d and the geometric difference g with classical ML models for quantum kernel (Q) and projected quantum kernel (PQ) under different embeddings and system sizes n. b Prediction error (lower is better) of the quantum kernel method (Q), projected quantum kernel method (PQ), and classical ML models on classical (C) and quantum (Q) datasets with number of data N = 600. As d grows too large, the geometric difference g for quantum kernel becomes small. We see that small geometric difference g always results in classical ML being competitive or outperforming the quantum ML model. When g is large, there is a potential for improvement over classical ML. For example, projected quantum kernel improves upon the best classical ML in Dataset (Q, E3).
Fig. 3 Relation between dimension d, geometric difference g, and prediction performance. The shaded regions are the standard deviation over 10 independent runs and n is the number of qubits in the quantum encoding and dimension of the input for the classical encoding. a The approximate dimension d and the geometric difference g with classical ML models for quantum kernel (Q) and projected quantum kernel (PQ) under different embeddings and system sizes n. b Prediction error (lower is better) of the quantum kernel method (Q), projected quantum kernel method (PQ), and classical ML models on classical (C) and quantum (Q) datasets with number of data N = 600. As d grows too large, the geometric difference g for quantum kernel becomes small. We see that small geometric difference g always results in classical ML being competitive or outperforming the quantum ML model. When g is large, there is a potential for improvement over classical ML. For example, projected quantum kernel improves upon the best classical ML in Dataset (Q, E3).CC BY · PubMed Central
Fig. 4 Prediction accuracy (higher the better) on engineered datasets. A label function is engineered to match the geometric difference g(C∣∣PQ) between projected quantum kernel and classical approaches, demonstrating a significant gap between quantum and the best classical models up to 30 qubits when g is large. We consider the best performing classical ML models among Gaussian SVM, linear SVM, Adaboost, random forest, neural networks, and gradient boosting. We only report the accuracy of the quantum kernel method up to system size n = 28 due to the high simulation cost and the inferior performance.
Fig. 4 Prediction accuracy (higher the better) on engineered datasets. A label function is engineered to match the geometric difference g(C∣∣PQ) between projected quantum kernel and classical approaches, demonstrating a significant gap between quantum and the best classical models up to 30 qubits when g is large. We consider the best performing classical ML models among Gaussian SVM, linear SVM, Adaboost, random forest, neural networks, and gradient boosting. We only report the accuracy of the quantum kernel method up to system size n = 28 due to the high simulation cost and the inferior performance.CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 67 references

Cited by

See all 924

Metadata

Authors
Huang, H.-Y., Broughton, M., Mohseni, M., Babbush, R., Boixo, S., Neven, H., & McClean, J. R.
Affiliations
  • California Institute of Technology (US)
  • Google (United States) (US)
Corresponding author
McClean, Jarrod R.
Venue
Nature Communications
Published
2021-05-11
Volume
12
Issue
1
Pages
2631-2631
ISSN
2041-1723 (ISSN-L)
OpenAlex
W3096052452
Cited by
896
References
67
Citations by year
2026: 220 · 2025: 220 · 2024: 157 · 2023: 140 · 2022: 107 · 2021: 52
FWCI
39.93
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • CaltechAUTHORS (California Institute of Technology) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • arXiv (Cornell University)
  • Bulletin of the American Physical Society
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum many-body systems
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum Information and Cryptography
Keywords
quantum machine learning, quantum advantage, prediction error bounds, classical machine learning, fault-tolerant quantum computing, gate-based quantum computing, quantum-classical comparison

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: Power of data in quantum machine learning. https://app.cochat.ai/papers/10.1038/s41467-021-22539-9
The paper
Huang, H.-Y., Broughton, M., Mohseni, M., Babbush, R., Boixo, S., Neven, H., & McClean, J. R. (2021). Power of data in quantum machine learning. Nature Communications. https://doi.org/10.1038/s41467-021-22539-9

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.