Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.21569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917315516301312 |
|---|---|
| author | Kimura, Takeshi Kato, Kohtaro Hayashi, Masahito |
| author_facet | Kimura, Takeshi Kato, Kohtaro Hayashi, Masahito |
| contents | Quantum Boltzmann machines (QBMs) are generative models with potential advantages in quantum machine learning, yet their training is fundamentally limited by the barren plateau problem, where gradients vanish exponentially with system size. We introduce a quantum version of the em algorithm, an information-geometric generalization of the classical Expectation-Maximization method, which circumvents gradient-based optimization on non-convex functions. Implemented on a semi-quantum restricted Boltzmann machine (sqRBM) -- a hybrid architecture with quantum effects confined to the hidden layer -- our method achieves stable learning and outperforms gradient descent on multiple benchmark datasets. These results establish a structured and scalable alternative to gradient-based training in QML, offering a pathway to mitigate barren plateaus and enhance quantum generative modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Structured quantum learning via em algorithm for Boltzmann machines Kimura, Takeshi Kato, Kohtaro Hayashi, Masahito Quantum Physics Machine Learning Quantum Boltzmann machines (QBMs) are generative models with potential advantages in quantum machine learning, yet their training is fundamentally limited by the barren plateau problem, where gradients vanish exponentially with system size. We introduce a quantum version of the em algorithm, an information-geometric generalization of the classical Expectation-Maximization method, which circumvents gradient-based optimization on non-convex functions. Implemented on a semi-quantum restricted Boltzmann machine (sqRBM) -- a hybrid architecture with quantum effects confined to the hidden layer -- our method achieves stable learning and outperforms gradient descent on multiple benchmark datasets. These results establish a structured and scalable alternative to gradient-based training in QML, offering a pathway to mitigate barren plateaus and enhance quantum generative modeling. |
| title | Structured quantum learning via em algorithm for Boltzmann machines |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2507.21569 |