Academic Journal
Provably Trainable Rotationally Equivariant Quantum Machine Learning
| العنوان: | Provably Trainable Rotationally Equivariant Quantum Machine Learning |
|---|---|
| المؤلفون: | West, Maxwell T., Heredge, Jamie, Sevior, Martin, Usman, Muhammad |
| المساهمون: | Australian Research Council, National Computing Infrastructure, Pawsey Supercomputing Research Center, National Computational Merit Allocation Scheme, The University of Melbourne’s Research Computing Services, the Petascale Campus Initiative |
| المصدر: | PRX Quantum ; volume 5, issue 3 ; ISSN 2691-3399 |
| بيانات النشر: | American Physical Society (APS) |
| سنة النشر: | 2024 |
| الوصف: | Exploiting the power of quantum computation to realize superior machine learning algorithms has been a major research focus of recent years, but the prospects of quantum machine learning (QML) remain dampened by considerable technical challenges. A particularly significant issue is that generic QML models suffer from so-called barren plateaus in their training landscapes—large regions where cost function gradients vanish exponentially in the number of qubits employed, rendering large models effectively untrainable. A leading strategy for combating this effect is to build problem-specific models that take into account the symmetries of their data in order to focus on a smaller, relevant subset of Hilbert space. In this work, we introduce a family of rotationally equivariant QML models built upon the quantum Fourier transform, and leverage recent insights from the Lie-algebraic study of QML models to prove that (a subset of) our models do not exhibit barren plateaus. In addition to our analytical results we numerically test our rotationally equivariant models on a dataset of simulated scanning tunneling microscope images of phosphorus impurities in silicon, where rotational symmetry naturally arises, and find that they dramatically outperform their generic counterparts in practice. Published by the American Physical Society 2024 |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1103/prxquantum.5.030320 |
| DOI: | 10.1103/PRXQuantum.5.030320 |
| DOI: | 10.1103/PRXQuantum.5.030320/fulltext |
| الاتاحة: | http://dx.doi.org/10.1103/prxquantum.5.030320 https://link.aps.org/article/10.1103/PRXQuantum.5.030320 http://harvest.aps.org/v2/journals/articles/10.1103/PRXQuantum.5.030320/fulltext |
| Rights: | https://creativecommons.org/licenses/by/4.0/ |
| رقم الانضمام: | edsbas.73B8CE1 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1103/prxquantum.5.030320 |
|---|