| Home > Publications database > Expressive equivalence of classical and quantum restricted Boltzmann machines |
| Typ | Amount | VAT | Currency | Share | Status | Cost centre |
| APC | 3075.35 | 0.00 | EUR | 96.85 % | (DEAL) | 9001010 / 476152 |
| Payment fee | 100.00 | 0.35 | EUR | 3.15 % | (Bestellt) | 9001010 / 476152 |
| Sum | 3175.35 | 0.35 | EUR | |||
| Total | 3175.70 |
| Journal Article | PUBDB-2025-01234 |
; ; ; ;
2025
Springer Nature
London
This record in other databases:
Please use a persistent id in citations: doi:10.1038/s42005-025-02353-1 doi:10.3204/PUBDB-2025-01234
Report No.: arXiv:2502.17562
Abstract: The development of generative models for quantum machine learning has faced challenges such as trainability and scalability. A notable example is the quantum restricted Boltzmann machine (QRBM), where non-commuting Hamiltonians make gradient evaluation computationally demanding, even on fault-tolerant devices. In this work, we propose a semi-quantum restricted Boltzmann machine (sqRBM), a model designed to overcome difficulties associated with QRBMs. The sqRBM Hamiltonian commutes in the visible subspace while remaining non-commuting in the hidden subspace, enabling us to derive closed-form expressions for output probabilities and gradients. Our analysis shows that, for learning a given distribution, a classical model requires three times more hidden units than an sqRBM. Numerical simulations with up to 100 units validate this prediction. With reduced resource demands, sqRBMs provide a feasible framework for early quantum generative models.
|
The record appears in these collections: |
Preprint
Expressive equivalence of classical and quantum restricted Boltzmann machines
Files
Fulltext by arXiv.org
BibTeX |
EndNote:
XML,
Text |
RIS