Entanglement-induced provable and robust quantum learning advantages
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911084055625728 |
|---|---|
| author | Zhao, Haimeng Deng, Dong-Ling |
| author_facet | Zhao, Haimeng Deng, Dong-Ling |
| contents | Quantum computing holds unparalleled potentials to enhance machine learning. However, a demonstration of quantum learning advantage has not been achieved so far. We make a step forward by rigorously establishing a noise-robust, unconditional quantum learning advantage in expressivity, inference speed, and training efficiency, compared to commonly-used classical models. Our proof is information-theoretic and pinpoints the origin of this advantage: entanglement can be used to reduce the communication required by non-local tasks. In particular, we design a task that can be solved with certainty by quantum models with a constant number of parameters using entanglement, whereas commonly-used classical models must scale linearly to achieve a larger-than-exponentially-small accuracy. We show that the quantum model is trainable with constant resources and robust against constant noise. Through numerical and trapped-ion experiments on IonQ Aria, we demonstrate the desired advantage. Our results provide valuable guidance for demonstrating quantum learning advantages with current noisy intermediate-scale devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03094 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Entanglement-induced provable and robust quantum learning advantages Zhao, Haimeng Deng, Dong-Ling Quantum Physics Computational Complexity Machine Learning Quantum computing holds unparalleled potentials to enhance machine learning. However, a demonstration of quantum learning advantage has not been achieved so far. We make a step forward by rigorously establishing a noise-robust, unconditional quantum learning advantage in expressivity, inference speed, and training efficiency, compared to commonly-used classical models. Our proof is information-theoretic and pinpoints the origin of this advantage: entanglement can be used to reduce the communication required by non-local tasks. In particular, we design a task that can be solved with certainty by quantum models with a constant number of parameters using entanglement, whereas commonly-used classical models must scale linearly to achieve a larger-than-exponentially-small accuracy. We show that the quantum model is trainable with constant resources and robust against constant noise. Through numerical and trapped-ion experiments on IonQ Aria, we demonstrate the desired advantage. Our results provide valuable guidance for demonstrating quantum learning advantages with current noisy intermediate-scale devices. |
| title | Entanglement-induced provable and robust quantum learning advantages |
| topic | Quantum Physics Computational Complexity Machine Learning |
| url | https://arxiv.org/abs/2410.03094 |