Generalization in Quantum Machine Learning: A Quantum Information Standpoint
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Quantum classification and hypothesis testing (state and channel discrimination) are two tightly related subjects, the main difference being that the former is data driven: how to assign to quantum states ρ(x) the corresponding class c (or hypothesis) is learnt from examples during training, where x can be either tunable experimental parameters or classical data "embedded" into quantum states.Does the model generalize?This is the main question in any data-driven strategy, namely the ability to predict the correct class even of previously unseen states.Here we establish a link between quantum classification and quantum information theory, by showing that the accuracy and generalization capability of quantum classifiers depend on the (Rényi) mutual information I (C:Q) and I 2 (X :Q) between the quantum state space Q and the classical parameter space X or class space C. Based on the above characterization, we then show how different properties of Q affect classification accuracy and generalization, such as the dimension of the Hilbert space, the amount of noise, and the amount of neglected information from X via, e.g., pooling layers.Moreover, we introduce a quantum version of the information bottleneck principle that allows us to explore the various trade-offs between accuracy and generalization.Finally, in order to check our theoretical predictions, we study the classification of the quantum phases of an Ising spin chain, and we propose the variational quantum information bottleneck method to optimize quantum embeddings of classical data to favor generalization.
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
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
Understanding Machine Learning: From Theory to Algorithms
Shalev-Shwartz, S., & Ben-David, S. (2014) · doi:10.1017/cbo9781107298019 · Cited by 3,115
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 2×
“In classical settings, a method designed for this purpose is the information bottleneck (IB) principle [27, 41], which allows us to find the “best” compressed representation Z of the input X that nonetheless has all the relevant information required to predict the class C.”
BackgroundMethodSupervised 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
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×
“In this panorama, many works have considered and designed learning models that are built by using quantum states and algorithms [5–19].”
BackgroundMitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018) · Physical Review A · doi:10.1103/physreva.98.032309 · Cited by 1,639 · cited 1×
“%) and low B , while for large values of β ≥ 2, we find that R approaches the theoretical lower bound (Bayes risk), but at the expense of a larger generalization error, as B gets close to the theoretical upper bound (16).”
BackgroundReconciling modern machine-learning practice and the classical bias–variance trade-off
Belkin, M., Hsu, D., Ma, S., & Mandal, S. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1903070116 · Cited by 1,595
Quantum convolutional neural networks
Cong, I., Choi, S., & Lukin, M. D. (2019) · Nature Physics · doi:10.1038/s41567-019-0648-8 · Cited by 1,517 · cited 4×
“QCNNs have some desirable features, such as the ability to distinguish states corresponding to complex phases of matter [9], and the lack of barren plateaus in their parameter landscape [47], which aids training.”
BackgroundMethodInfluentialGeometry of Quantum States: An Introduction to Quantum Entanglement
Bengtsson, I., & Zyczkowski, K. (2006) · doi:10.1017/cbo9780511535048 · Cited by 1,357
The Theory of Quantum Information
Watrous, J. (2018) · doi:10.1017/9781316848142 · Cited by 1,325
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
Generalization 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
Biology and medicine in the landscape of quantum advantages
Cordier, B. A., Sawaya, N. P. D., Guerreschi, G. G., & McWeeney, S. K. (2022) · Journal of The Royal Society Interface · doi:10.1098/rsif.2022.0541 · Cited by 87
“Advantages in generalization error are dependent on a variety of factors, including the encoding used (with basis encoding performing particularly poorly [416]) and the availability of data sufficient to train a comparable classical model [225].”
BackgroundTowards quantum enhanced adversarial robustness in machine learning
West, M. T., Tsang, S.-L., Low, J. S., Hill, C. D., Leckie, C., Hollenberg, L. C. L., Erfani, S. M., & Usman, M. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00661-1 · Cited by 79
Metadata
- Authors
- Banchi, L., Pereira, J., & Pirandola, S.
- Venue
- PRX Quantum
- Publisher
- American Physical Society (APS)
- Published
- 2021-11-01
- Volume
- 2
- Issue
- 4
- ISSN
- 2691-3399 (ISSN-L)
- OpenAlex
- W3211028885
- Cited by
- 153
- References
- 23
- FWCI
- 8.65
- Type
- journal article
- Language
- en
- Open access
- gold
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.