Generalization in quantum machine learning from few training data
The power of quantum machine learning algorithms based on parametrised quantum circuits are still not fully understood. Here, the authors report rigorous bounds on the generalisation error in variational QML, confirming how known implementable models generalize well from an efficient amount of train...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-08-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-022-32550-3 |
| _version_ | 1817998801613357056 |
|---|---|
| author | Matthias C. Caro Hsin-Yuan Huang M. Cerezo Kunal Sharma Andrew Sornborger Lukasz Cincio Patrick J. Coles |
| author_facet | Matthias C. Caro Hsin-Yuan Huang M. Cerezo Kunal Sharma Andrew Sornborger Lukasz Cincio Patrick J. Coles |
| author_sort | Matthias C. Caro |
| collection | DOAJ |
| description | The power of quantum machine learning algorithms based on parametrised quantum circuits are still not fully understood. Here, the authors report rigorous bounds on the generalisation error in variational QML, confirming how known implementable models generalize well from an efficient amount of training data. |
| first_indexed | 2024-04-14T02:58:27Z |
| format | Article |
| id | doaj.art-b4bb435a92dd4f239c5b6469734606ea |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-14T02:58:27Z |
| publishDate | 2022-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-b4bb435a92dd4f239c5b6469734606ea2022-12-22T02:16:00ZengNature PortfolioNature Communications2041-17232022-08-0113111110.1038/s41467-022-32550-3Generalization in quantum machine learning from few training dataMatthias C. Caro0Hsin-Yuan Huang1M. Cerezo2Kunal Sharma3Andrew Sornborger4Lukasz Cincio5Patrick J. Coles6Department of Mathematics, Technical University of MunichInstitute for Quantum Information and Matter, CaltechInformation Sciences, Los Alamos National LaboratoryJoint Center for Quantum Information and Computer Science, University of MarylandInformation Sciences, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryThe power of quantum machine learning algorithms based on parametrised quantum circuits are still not fully understood. Here, the authors report rigorous bounds on the generalisation error in variational QML, confirming how known implementable models generalize well from an efficient amount of training data.https://doi.org/10.1038/s41467-022-32550-3 |
| spellingShingle | Matthias C. Caro Hsin-Yuan Huang M. Cerezo Kunal Sharma Andrew Sornborger Lukasz Cincio Patrick J. Coles Generalization in quantum machine learning from few training data Nature Communications |
| title | Generalization in quantum machine learning from few training data |
| title_full | Generalization in quantum machine learning from few training data |
| title_fullStr | Generalization in quantum machine learning from few training data |
| title_full_unstemmed | Generalization in quantum machine learning from few training data |
| title_short | Generalization in quantum machine learning from few training data |
| title_sort | generalization in quantum machine learning from few training data |
| url | https://doi.org/10.1038/s41467-022-32550-3 |
| work_keys_str_mv | AT matthiasccaro generalizationinquantummachinelearningfromfewtrainingdata AT hsinyuanhuang generalizationinquantummachinelearningfromfewtrainingdata AT mcerezo generalizationinquantummachinelearningfromfewtrainingdata AT kunalsharma generalizationinquantummachinelearningfromfewtrainingdata AT andrewsornborger generalizationinquantummachinelearningfromfewtrainingdata AT lukaszcincio generalizationinquantummachinelearningfromfewtrainingdata AT patrickjcoles generalizationinquantummachinelearningfromfewtrainingdata |