The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Theory of overparametrization in quantum neural networks
Open accessAbstract
The prospect of achieving quantum advantage with quantum neural networks (QNNs) is exciting. Understanding how QNN properties (for example, the number of parameters M) affect the loss landscape is crucial to designing scalable QNN architectures. Here we rigorously analyze the overparametrization phenomenon in QNNs, defining overparametrization as the regime where the QNN has more than a critical number of parameters Mc allowing it to explore all relevant directions in state space. Our main results show that the dimension of the Lie algebra obtained from the generators of the QNN is an upper bound for Mc, and for the maximal rank that the quantum Fisher information and Hessian matrices can reach. Underparametrized QNNs have spurious local minima in the loss landscape that start disappearing when M ≥ Mc. Thus, the overparametrization onset corresponds to a computational phase transition where the QNN trainability is greatly improved. We then connect the notion of overparametrization to the QNN capacity, so that when a QNN is overparametrized, its capacity achieves its maximum possible value. A theoretical framework for quantum neural network (QNN) overparametrization, a phase transition in loss landscape complexity, is established. The precise characterization of the critical number of parameters offered is expected to impact QNN design.
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.
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
Quantum Computation and Quantum Information
Nielsen, M. A., Chuang, I., & Grover, L. K. (2002) · American Journal of Physics · doi:10.1119/1.1463744 · Cited by 21,895
Quantum Computing in the NISQ era and beyond
Preskill, J. (2018) · Quantum · doi:10.22331/q-2018-08-06-79 · Cited by 8,830
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
A variational eigenvalue solver on a photonic quantum processor
Peruzzo, A., McClean, J., Shadbolt, P., Yung, M.-H., Zhou, X.-Q., Love, P. J., Aspuru-Guzik, A., & O’Brien, J. L. (2014) · Nature Communications · doi:10.1038/ncomms5213 · Cited by 4,552 · cited 1×
“First, we use the VQE algorithm [103–105] to minimize the loss function and find the ground state of the Hamiltonian of the transverse field Ising model H TFIM .”
MethodVariational quantum algorithms
Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S. C., Endo, S., Fujii, K., McClean, J. R., Mitarai, K., Yuan, X., Cincio, L., et al. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00348-9 · Cited by 3,385 · cited 1×
“F̃(θ) G EE[ ∂ log(p(||ψμ⟩ , yμ; θ)) ∂θ ∂ log(p(||ψμ⟩ , yμ; θ)) ∂θ T ] (10)”
Self-citationApplications of machine learning in drug discovery and development
Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/s41573-019-0024-5 · Cited by 3,228
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
Understanding deep learning (still) requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021) · Communications of the ACM · doi:10.1145/3446776 · Cited by 2,400 · cited 2×
“Usually, this implies having a number of parameters in the NN ∗ The first two authors contributed equally to this work. that is much larger than the number of training points [9].”
BackgroundNoisy intermediate-scale quantum algorithms
Bharti, K., Cervera-Lierta, A., Kyaw, T. H., Haug, T., Alperin-Lea, S., Anand, A., Degroote, M., Heimonen, H., Kottmann, J. S., Menke, T., et al. (2022) · Reviews of Modern Physics · doi:10.1103/revmodphys.94.015004 · Cited by 2,231 · cited 1×
“Such loss functions arise for supervised quantum machine learning [43, 44, 91], autoencoding [92], principal component analysis [93–95], dynamical simulation [96–99], and, more generally, for variational quantum algorithms [20, 100].”
BackgroundMitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018) · Physical Review A · doi:10.1103/physreva.98.032309 · Cited by 1,639 · cited 2×
“Finally, we mention that parameter-shift rules [133, 134] have been employed in all cases for the computation of the quantum Fisher information and Hessian matrices, and that the simulation backend was switched to the faster qibojit for that.”
BackgroundMethod
Cited by
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
Self-citationGeneralization 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
Self-citationBarren plateaus in variational quantum computing
Larocca, M., Thanasilp, S., Wang, S., Sharma, K., Biamonte, J., Coles, P. J., Cincio, L., McClean, J. R., Holmes, Z., & Cerezo, M. (2025) · Nature Reviews Physics · doi:10.1038/s42254-025-00813-9 · Cited by 257
Self-citation
Metadata
- Authors
- Larocca, M., Ju, N., García-Martín, D., Coles, P. J., & Cerezo, M.
- Venue
- Nature Computational Science
- Published
- 2023-06-26
- Volume
- 3
- Issue
- 6
- Pages
- 542-551
- ISSN
- 2662-8457 (ISSN-L)
- OpenAlex
- W3201979454
- Cited by
- 176
- References
- 46
- FWCI
- 14.23
- Type
- journal article
- Language
- en
- Open access
- green
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: Theory of overparametrization in quantum neural networks. https://app.cochat.ai/papers/10.1038/s43588-023-00467-6
- The paper
- Larocca, M., Ju, N., García-Martín, D., Coles, P. J., & Cerezo, M. (2023). Theory of overparametrization in quantum neural networks. Nature Computational Science. https://doi.org/10.1038/s43588-023-00467-6
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.