Double descent in quantum kernel methods
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908770032943104 |
|---|---|
| author | Kempkes, Marie Ijaz, Aroosa Gil-Fuster, Elies Bravo-Prieto, Carlos Spiegelberg, Jakob van Nieuwenburg, Evert Dunjko, Vedran |
| author_facet | Kempkes, Marie Ijaz, Aroosa Gil-Fuster, Elies Bravo-Prieto, Carlos Spiegelberg, Jakob van Nieuwenburg, Evert Dunjko, Vedran |
| contents | The double descent phenomenon challenges traditional statistical learning theory by revealing scenarios where larger models do not necessarily lead to reduced performance on unseen data. While this counterintuitive behavior has been observed in a variety of classical machine learning models, particularly modern neural network architectures, it remains elusive within the context of quantum machine learning. In this work, we analytically demonstrate that linear regression models in quantum feature spaces can exhibit double descent behavior by drawing on insights from classical linear regression and random matrix theory. Additionally, our numerical experiments on quantum kernel methods across different real-world datasets and system sizes further confirm the existence of a test error peak, a characteristic feature of double descent. Our findings provide evidence that quantum models can operate in the modern, overparameterized regime without experiencing overfitting, potentially opening pathways to improved learning performance beyond traditional statistical learning theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Double descent in quantum kernel methods Kempkes, Marie Ijaz, Aroosa Gil-Fuster, Elies Bravo-Prieto, Carlos Spiegelberg, Jakob van Nieuwenburg, Evert Dunjko, Vedran Quantum Physics Machine Learning The double descent phenomenon challenges traditional statistical learning theory by revealing scenarios where larger models do not necessarily lead to reduced performance on unseen data. While this counterintuitive behavior has been observed in a variety of classical machine learning models, particularly modern neural network architectures, it remains elusive within the context of quantum machine learning. In this work, we analytically demonstrate that linear regression models in quantum feature spaces can exhibit double descent behavior by drawing on insights from classical linear regression and random matrix theory. Additionally, our numerical experiments on quantum kernel methods across different real-world datasets and system sizes further confirm the existence of a test error peak, a characteristic feature of double descent. Our findings provide evidence that quantum models can operate in the modern, overparameterized regime without experiencing overfitting, potentially opening pathways to improved learning performance beyond traditional statistical learning theory. |
| title | Double descent in quantum kernel methods |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2501.10077 |