Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.20798 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908607819284480 |
|---|---|
| author | Orquin-Marques, Jose J. Flores-Garrigos, Carlos Cadavid, Alejandro Gomez Simen, Anton Solano, Enrique Hegade, Narendra N. Martin-Guerrero, Jose D. Vives-Gilabert, Yolanda |
| author_facet | Orquin-Marques, Jose J. Flores-Garrigos, Carlos Cadavid, Alejandro Gomez Simen, Anton Solano, Enrique Hegade, Narendra N. Martin-Guerrero, Jose D. Vives-Gilabert, Yolanda |
| contents | We present a quantum-native approach to quantum feature selection (QFS) based on analog quantum simulation with neutral atom arrays, adaptable to a variety of academic and industrial applications. In our method, feature relevance-measured via mutual information with the target-is encoded as local detuning amplitudes, while feature redundancy is embedded through distance-dependent van der Waals interactions, constrained by the Rydberg blockade radius. The system is evolved adiabatically toward low-energy configurations, and the resulting measurement bitstrings are used to extract physically consistent subsets of features. The protocol is evaluated through simulations on three benchmark binary classification datasets: Adult Income, Bank Marketing, and Telco Churn. Compared to classical methods such as mutual information ranking and Boruta, combined with XGBoost and Random Forest classifiers, our quantum-computing approach achieves competitive or superior performance. In particular, for compact subsets of 2-5 features, analog QFS improves mean AUC scores by 1.5-2.3% while reducing the number of features by 75-84%, offering interpretable, low-redundancy solutions. These results demonstrate that programmable Rydberg arrays offer a viable platform for intelligent feature selection with practical relevance in machine learning pipelines, capable of transforming computational quantum advantage into industrial quantum usefulness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20798 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Analog Quantum Feature Selection with Neutral-Atom Quantum Processors Orquin-Marques, Jose J. Flores-Garrigos, Carlos Cadavid, Alejandro Gomez Simen, Anton Solano, Enrique Hegade, Narendra N. Martin-Guerrero, Jose D. Vives-Gilabert, Yolanda Quantum Physics We present a quantum-native approach to quantum feature selection (QFS) based on analog quantum simulation with neutral atom arrays, adaptable to a variety of academic and industrial applications. In our method, feature relevance-measured via mutual information with the target-is encoded as local detuning amplitudes, while feature redundancy is embedded through distance-dependent van der Waals interactions, constrained by the Rydberg blockade radius. The system is evolved adiabatically toward low-energy configurations, and the resulting measurement bitstrings are used to extract physically consistent subsets of features. The protocol is evaluated through simulations on three benchmark binary classification datasets: Adult Income, Bank Marketing, and Telco Churn. Compared to classical methods such as mutual information ranking and Boruta, combined with XGBoost and Random Forest classifiers, our quantum-computing approach achieves competitive or superior performance. In particular, for compact subsets of 2-5 features, analog QFS improves mean AUC scores by 1.5-2.3% while reducing the number of features by 75-84%, offering interpretable, low-redundancy solutions. These results demonstrate that programmable Rydberg arrays offer a viable platform for intelligent feature selection with practical relevance in machine learning pipelines, capable of transforming computational quantum advantage into industrial quantum usefulness. |
| title | Analog Quantum Feature Selection with Neutral-Atom Quantum Processors |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2510.20798 |