Explicit quantum surrogates for quantum kernel models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917125995626496 |
|---|---|
| author | Nakayama, Akimoto Morisaki, Hayata Mitarai, Kosuke Ueda, Hiroshi Fujii, Keisuke |
| author_facet | Nakayama, Akimoto Morisaki, Hayata Mitarai, Kosuke Ueda, Hiroshi Fujii, Keisuke |
| contents | Quantum machine learning (QML) leverages quantum states for data encoding, with key approaches being explicit models that use parameterized quantum circuits and implicit models that use quantum kernels. Implicit models often have lower training errors but face issues such as overfitting and high prediction costs, while explicit models can struggle with complex training and barren plateaus. We propose a quantum-classical hybrid algorithm to create an explicit quantum surrogate (EQS) for trained implicit models. This involves diagonalizing an observable from the implicit model and constructing a corresponding quantum circuit using an extended automatic quantum circuit encoding algorithm. The EQS framework reduces prediction costs, provides a powerful strategy to mitigate barren plateau issues, and combines the strengths of both QML approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03000 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explicit quantum surrogates for quantum kernel models Nakayama, Akimoto Morisaki, Hayata Mitarai, Kosuke Ueda, Hiroshi Fujii, Keisuke Quantum Physics Quantum machine learning (QML) leverages quantum states for data encoding, with key approaches being explicit models that use parameterized quantum circuits and implicit models that use quantum kernels. Implicit models often have lower training errors but face issues such as overfitting and high prediction costs, while explicit models can struggle with complex training and barren plateaus. We propose a quantum-classical hybrid algorithm to create an explicit quantum surrogate (EQS) for trained implicit models. This involves diagonalizing an observable from the implicit model and constructing a corresponding quantum circuit using an extended automatic quantum circuit encoding algorithm. The EQS framework reduces prediction costs, provides a powerful strategy to mitigate barren plateau issues, and combines the strengths of both QML approaches. |
| title | Explicit quantum surrogates for quantum kernel models |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2408.03000 |