Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917508219404288 |
|---|---|
| author | Tokuhiro, Lena Bentellis, Amine Lorenz, Jeanette Miriam |
| author_facet | Tokuhiro, Lena Bentellis, Amine Lorenz, Jeanette Miriam |
| contents | Quantum machine learning (QML) has attracted considerable research interest, yet whether it offers practical benefits over classical approaches remains an open question. The choice of data encoding significantly influences QML performance, but why certain encodings outperform others remains poorly understood. We employ Monte Carlo Tree Search (MCTS) to discover optimal data encoding circuits for a quantum-classical convolutional neural network (QCCNN) combining a non-variational quantum block for feature extraction with a classical classifier. Evaluating on two medical imaging datasets, the discovered circuits outperform commonly used encoding strategies while showing competitive results compared to purely classical counterparts. We further analyze metrics to identify predictors of encoding performance. Entanglement capability and Fourier decomposition provide minimal insight, whereas the effective rank of the feature maps exhibits meaningful correlation and can serve as a threshold criterion to accelerate the search for high-performing encodings. Our findings provide both a practical method for encoding discovery and new insights into what makes data encodings effective in QML. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18540 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search Tokuhiro, Lena Bentellis, Amine Lorenz, Jeanette Miriam Quantum Physics Quantum machine learning (QML) has attracted considerable research interest, yet whether it offers practical benefits over classical approaches remains an open question. The choice of data encoding significantly influences QML performance, but why certain encodings outperform others remains poorly understood. We employ Monte Carlo Tree Search (MCTS) to discover optimal data encoding circuits for a quantum-classical convolutional neural network (QCCNN) combining a non-variational quantum block for feature extraction with a classical classifier. Evaluating on two medical imaging datasets, the discovered circuits outperform commonly used encoding strategies while showing competitive results compared to purely classical counterparts. We further analyze metrics to identify predictors of encoding performance. Entanglement capability and Fourier decomposition provide minimal insight, whereas the effective rank of the feature maps exhibits meaningful correlation and can serve as a threshold criterion to accelerate the search for high-performing encodings. Our findings provide both a practical method for encoding discovery and new insights into what makes data encodings effective in QML. |
| title | Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2605.18540 |