Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918470129549312 |
|---|---|
| author | Ordóñez, Sebastian Cajas Osorio, Felipe Ocampo Koh, Dax Enshan Attrach, Rafi Al Marzullo, Aldo Guerra-Adames, Ariel Andrade, J. Alejandro Goh, Siong Thye Chen, Chi-Yu Gorijavolu, Rahul Yang, Xue Hebdon, Noah Dane Celi, Leo Anthony |
| author_facet | Ordóñez, Sebastian Cajas Osorio, Felipe Ocampo Koh, Dax Enshan Attrach, Rafi Al Marzullo, Aldo Guerra-Adames, Ariel Andrade, J. Alejandro Goh, Siong Thye Chen, Chi-Yu Gorijavolu, Rahul Yang, Xue Hebdon, Noah Dane Celi, Leo Anthony |
| contents | We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings Ordóñez, Sebastian Cajas Osorio, Felipe Ocampo Koh, Dax Enshan Attrach, Rafi Al Marzullo, Aldo Guerra-Adames, Ariel Andrade, J. Alejandro Goh, Siong Thye Chen, Chi-Yu Gorijavolu, Rahul Yang, Xue Hebdon, Noah Dane Celi, Leo Anthony Quantum Physics Artificial Intelligence We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage |
| title | Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings |
| topic | Quantum Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2604.24597 |