Quantum machine learning beyond kernel methods
Comparing the capabilities of different quantum machine learning protocols is difficult. Here, the authors show that different learning models based on parametrized quantum circuits can all be seen as quantum linear models, thus driving general conclusions on their resource requirements and capabili...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-36159-y |
| _version_ | 1811171657299001344 |
|---|---|
| author | Sofiene Jerbi Lukas J. Fiderer Hendrik Poulsen Nautrup Jonas M. Kübler Hans J. Briegel Vedran Dunjko |
| author_facet | Sofiene Jerbi Lukas J. Fiderer Hendrik Poulsen Nautrup Jonas M. Kübler Hans J. Briegel Vedran Dunjko |
| author_sort | Sofiene Jerbi |
| collection | DOAJ |
| description | Comparing the capabilities of different quantum machine learning protocols is difficult. Here, the authors show that different learning models based on parametrized quantum circuits can all be seen as quantum linear models, thus driving general conclusions on their resource requirements and capabilities. |
| first_indexed | 2024-04-10T17:17:36Z |
| format | Article |
| id | doaj.art-be9a37f1040943988bb2f3b9570a8b1a |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-10T17:17:36Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-be9a37f1040943988bb2f3b9570a8b1a2023-02-05T12:17:32ZengNature PortfolioNature Communications2041-17232023-01-011411810.1038/s41467-023-36159-yQuantum machine learning beyond kernel methodsSofiene Jerbi0Lukas J. Fiderer1Hendrik Poulsen Nautrup2Jonas M. Kübler3Hans J. Briegel4Vedran Dunjko5Institute for Theoretical Physics, University of InnsbruckInstitute for Theoretical Physics, University of InnsbruckInstitute for Theoretical Physics, University of InnsbruckMax Planck Institute for Intelligent SystemsInstitute for Theoretical Physics, University of InnsbruckLeiden UniversityComparing the capabilities of different quantum machine learning protocols is difficult. Here, the authors show that different learning models based on parametrized quantum circuits can all be seen as quantum linear models, thus driving general conclusions on their resource requirements and capabilities.https://doi.org/10.1038/s41467-023-36159-y |
| spellingShingle | Sofiene Jerbi Lukas J. Fiderer Hendrik Poulsen Nautrup Jonas M. Kübler Hans J. Briegel Vedran Dunjko Quantum machine learning beyond kernel methods Nature Communications |
| title | Quantum machine learning beyond kernel methods |
| title_full | Quantum machine learning beyond kernel methods |
| title_fullStr | Quantum machine learning beyond kernel methods |
| title_full_unstemmed | Quantum machine learning beyond kernel methods |
| title_short | Quantum machine learning beyond kernel methods |
| title_sort | quantum machine learning beyond kernel methods |
| url | https://doi.org/10.1038/s41467-023-36159-y |
| work_keys_str_mv | AT sofienejerbi quantummachinelearningbeyondkernelmethods AT lukasjfiderer quantummachinelearningbeyondkernelmethods AT hendrikpoulsennautrup quantummachinelearningbeyondkernelmethods AT jonasmkubler quantummachinelearningbeyondkernelmethods AT hansjbriegel quantummachinelearningbeyondkernelmethods AT vedrandunjko quantummachinelearningbeyondkernelmethods |