Information-Theoretic Bounds on Quantum Advantage in Machine Learning
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter x and involve execution of a (possibly unknown) quantum process E. Our figure of merit is the number of runs of E required to achieve a desired prediction performance. We consider classical ML models that perform a measurement and record the classical outcome after each run of E, and quantum ML models that can access E coherently to acquire quantum data; the classical or quantum data are then used to predict the outcomes of future experiments. We prove that for any input distribution D(x), a classical ML model can provide accurate predictions on average by accessing E a number of times comparable to the optimal quantum ML model. In contrast, for achieving an accurate prediction on all inputs, we prove that the exponential quantum advantage is possible. For example, to predict the expectations of all Pauli observables in an n-qubit system ρ, classical ML models require 2^{Ω(n)} copies of ρ, but we present a quantum ML model using only O(n) copies. Our results clarify where the quantum advantage is possible and highlight the potential for classical ML models to address challenging quantum problems in physics and chemistry.
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
A new mixing of Hartree–Fock and local density-functional theories
Becke, A. D. (1993) · The Journal of Chemical Physics · doi:10.1063/1.464304 · Cited by 16,515
Quantum Computing in the NISQ era and beyond
Preskill, J. (2018) · Quantum · doi:10.22331/q-2018-08-06-79 · Cited by 8,830
Self-citationBiamonte, 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
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
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279
Density-matrix algorithms for quantum renormalization groups
White, S. R. (1993) · Physical Review B · doi:10.1103/physrevb.48.10345 · Cited by 3,244
Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets
Kandala, A., Mezzacapo, A., Temme, K., Takita, M., Brink, M., Chow, J. M., & Gambetta, J. M. (2017) · Nature · doi:10.1038/nature23879 · Cited by 2,982
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
Probing many-body dynamics on a 51-atom quantum simulator
Bernien, H., Schwartz, S., Keesling, A., Levine, H., Omran, A., Pichler, H., Choi, S., Zibrov, A. S., Endres, M., Greiner, M., et al. (2017) · Nature · doi:10.1038/nature24622 · Cited by 2,460
Solving the quantum many-body problem with artificial neural networks
Carleo, G., & Troyer, M. (2017) · Science · doi:10.1126/science.aag2302 · Cited by 2,215
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 · cited 3×
“Therefore, finding that classical and quantum ML have comparable power (for the average-case prediction) boosts our hopes that the combination of classical ML and nearterm quantum algorithms [2,3,25,28,47] may fruitfully address challenging quantum problems in physics, chemistry, and materials science.”
BackgroundQuantum convolutional neural networks
Cong, I., Choi, S., & Lukin, M. D. (2019) · Nature Physics · doi:10.1038/s41567-019-0648-8 · Cited by 1,517
Machine learning phases of matter
Carrasquilla, J., & Melko, R. G. (2017) · Nature Physics · doi:10.1038/nphys4035 · Cited by 1,448
Quantum principal component analysis
Lloyd, S., Mohseni, M., & Rebentrost, P. (2014) · Nature Physics · doi:10.1038/nphys3029 · Cited by 1,385
Predicting many properties of a quantum system from very few measurements
Huang, H.-Y., Kueng, R., & Preskill, J. (2020) · Nature Physics · doi:10.1038/s41567-020-0932-7 · Cited by 1,240
Self-citationFoundations of Machine Learning
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018) · doi:10.7551/mitpress/10290.001.0001 · Cited by 1,122
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
Self-citationBuluta, I., & Nori, F. (2009) · Science · doi:10.1126/science.1177838 · Cited by 876
Quantum lower bounds by polynomials
Beals, R., Buhrman, H., Cleve, R., Mosca, M., & de Wolf, R. (2001) · Journal of the ACM · doi:10.1145/502090.502097 · Cited by 639
Classification with Quantum Neural Networks on Near Term Processors
Farhi, E., & Neven, H. (2018) · arXiv · doi:10.48550/arxiv.1802.06002 · Cited by 598
Quantum algorithms for supervised and unsupervised machine learning
Lloyd, S., Mohseni, M., & Rebentrost, P. (2013) · arXiv · doi:10.48550/arxiv.1307.0411 · Cited by 542
Quantum Algorithm for Data Fitting
Wiebe, N., Braun, D., & Lloyd, S. (2012) · Physical Review Letters · doi:10.1103/physrevlett.109.050505 · Cited by 528
Geometry of Quantum States: An Introduction to Quantum Entanglement
Bengtsson, I., & Życzkowski, K. (2017) · doi:10.1017/9781139207010 · Cited by 525
A quantum-inspired classical algorithm for recommendation systems
Tang, E. (2019) · Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing · doi:10.1145/3313276.3316310 · Cited by 360
Measurement optimization in the variational quantum eigensolver using a minimum clique cover
Verteletskyi, V., Yen, T.-C., & Izmaylov, A. F. (2020) · The Journal of Chemical Physics · doi:10.1063/1.5141458 · Cited by 269
Efficient and noise resilient measurements for quantum chemistry on near-term quantum computers
Huggins, W. J., McClean, J. R., Rubin, N. C., Jiang, Z., Wiebe, N., Whaley, K. B., & Babbush, R. (2021) · npj Quantum Information · doi:10.1038/s41534-020-00341-7 · Cited by 256 · cited 1×
“muting observables [30,31]; See the Supplemental Material, App.”
BackgroundIzmaylov, A. F., Yen, T.-C., Lang, R. A., & Verteletskyi, V. (2020) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.9b00791 · Cited by 171 · cited 1×
“muting observables [30,31]; See the Supplemental Material, App.”
BackgroundGuest Column: A Survey of Quantum Learning Theory
Arunachalam, S., & de Wolf, R. (2017) · ACM SIGACT News · doi:10.1145/3106700.3106710 · Cited by 152
Tang, E. (2018) · arXiv · doi:10.48550/arxiv.1811.00414 · Cited by 141
Tang, E. (2021) · Physical Review Letters · doi:10.1103/physrevlett.127.060503 · Cited by 140
Near-term quantum algorithms for linear systems of equations
Huang, H.-Y., Bharti, K., & Rebentrost, P. (2019) · arXiv · doi:10.48550/arxiv.1909.07344 · Cited by 62
Self-citation
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
Self-citationChallenges 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-citationQuantum advantage in learning from experiments
Huang, H.-Y., Broughton, M., Cotler, J., Chen, S., Li, J., Mohseni, M., Neven, H., Babbush, R., Kueng, R., Preskill, J., et al. (2022) · Science · doi:10.1126/science.abn7293 · Cited by 519
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-citationBell Sampling from Quantum Circuits
Hangleiter, D., & Gullans, M. J. (2024) · Physical Review Letters · doi:10.1103/physrevlett.133.020601 · Cited by 28
Metadata
- Authors
- Huang, H.-Y., Kueng, R., & Preskill, J.
- Venue
- Physical Review Letters
- Publisher
- American Physical Society (APS)
- Published
- 2021-05-14
- Volume
- 126
- Issue
- 19
- Pages
- 190505-190505
- ISSN
- 0031-9007 (ISSN-L)
- 1079-7114
- OpenAlex
- W3119636101
- Cited by
- 250
- References
- 33
- FWCI
- 14.03
- 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
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.