Expressive equivalence of classical and quantum restricted Boltzmann machines

• URL: http://arxiv.org/abs/2502.17562v1
• Date: Mon, 24 Feb 2025 19:00:02 GMT
• Title: Expressive equivalence of classical and quantum restricted Boltzmann machines
• Authors: Maria Demidik, Cenk Tüysüz, Nico Piatkowski, Michele Grossi, Karl Jansen,
• Abstract summary: We propose a semi-quantum restricted Boltzmann machine (sqRBM) for classical data.<n> sqRBM is commuting in the visible subspace while remaining non-commuting in the hidden subspace.<n>Our theoretical analysis predicts that, to learn a given probability distribution, an RBM requires three times as many hidden units as an sqRBM.
• Score: 1.1639171061272031
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum computers offer the potential for efficiently sampling from complex probability distributions, attracting increasing interest in generative modeling within quantum machine learning. This surge in interest has driven the development of numerous generative quantum models, yet their trainability and scalability remain significant challenges. A notable example is a quantum restricted Boltzmann machine (QRBM), which is based on the Gibbs state of a parameterized non-commuting Hamiltonian. While QRBMs are expressive, their non-commuting Hamiltonians make gradient evaluation computationally demanding, even on fault-tolerant quantum computers. In this work, we propose a semi-quantum restricted Boltzmann machine (sqRBM), a model designed for classical data that mitigates the challenges associated with previous QRBM proposals. The sqRBM Hamiltonian is commuting in the visible subspace while remaining non-commuting in the hidden subspace. This structure allows us to derive closed-form expressions for both output probabilities and gradients. Leveraging these analytical results, we demonstrate that sqRBMs share a close relationship with classical restricted Boltzmann machines (RBM). Our theoretical analysis predicts that, to learn a given probability distribution, an RBM requires three times as many hidden units as an sqRBM, while both models have the same total number of parameters. We validate these findings through numerical simulations involving up to 100 units. Our results suggest that sqRBMs could enable practical quantum machine learning applications in the near future by significantly reducing quantum resource requirements.

Related papers

• Maximal Entropy Formalism and the Restricted Boltzmann Machine [1.7563879056963012]
  We introduce Restricted Boltzmann Machines (RBMs) as probabilistic models to approximate quantum states. We employ quantum sampling techniques to enhance RBM training, enabling scalable and high-fidelity quantum state reconstruction. Our method applies to the general and previously unaddressed case of reconstructing arbitrary mixed quantum states from incomplete and potentially non-commuting sets of expectations.
  arXiv  Detail & Related papers  (2025-04-04T17:57:20Z)
• Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines [0.0]
  We show that low-dimensional, fully-visible QBMs can learn to generate distributions typically associated with higher-dimensional systems. We find that non-commuting terms and Hamiltonian connectivity improve the learning capabilities of QBMs.
  arXiv  Detail & Related papers  (2024-10-21T18:00:01Z)
• On the Sample Complexity of Quantum Boltzmann Machine Learning [0.0]
  We give an operational definition of QBM learning in terms of the difference in expectation values between the model and target.<n>We prove that a solution can be obtained with gradient descent using at most a number of Gibbs states.<n>In particular, we give pre-training strategies based on mean-field, Gaussian Fermionic, and geometrically local Hamiltonians.
  arXiv  Detail & Related papers  (2023-06-26T18:00:50Z)
• Universality of critical dynamics with finite entanglement [68.8204255655161]
  We study how low-energy dynamics of quantum systems near criticality are modified by finite entanglement. Our result establishes the precise role played by entanglement in time-dependent critical phenomena.
  arXiv  Detail & Related papers  (2023-01-23T19:23:54Z)
• Importance sampling for stochastic quantum simulations [68.8204255655161]
  We introduce the qDrift protocol, which builds random product formulas by sampling from the Hamiltonian according to the coefficients. We show that the simulation cost can be reduced while achieving the same accuracy, by considering the individual simulation cost during the sampling stage. Results are confirmed by numerical simulations performed on a lattice nuclear effective field theory.
  arXiv  Detail & Related papers  (2022-12-12T15:06:32Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• Noisy Quantum Kernel Machines [58.09028887465797]
  An emerging class of quantum learning machines is that based on the paradigm of quantum kernels. We study how dissipation and decoherence affect their performance. We show that decoherence and dissipation can be seen as an implicit regularization for the quantum kernel machines.
  arXiv  Detail & Related papers  (2022-04-26T09:52:02Z)
• Bayesian Neural Networks for Fast SUSY Predictions [58.720142291102135]
  In this paper, machine learning is used to model the mapping from the parameter space of a BSM theory to some of its predictions. All three quantities are modeled with average percent errors of 3.34% or less and in a time significantly shorter than is possible with the supersymmetry codes from which the results are derived. Results are a further demonstration of the potential for machine learning to model accurately the mapping from the high dimensional spaces of BSM theories to their predictions.
  arXiv  Detail & Related papers  (2020-07-09T01:45:06Z)
• Exact representations of many body interactions with RBM neural networks [77.34726150561087]
  We exploit the representation power of RBMs to provide an exact decomposition of many-body contact interactions into one-body operators. This construction generalizes the well known Hirsch's transform used for the Hubbard model to more complicated theories such as Pionless EFT in nuclear physics.
  arXiv  Detail & Related papers  (2020-05-07T15:59:29Z)
• Effectively Trainable Semi-Quantum Restricted Boltzmann Machine [0.0]
  We propose a novel quantum model for the restricted Boltzmann machine (RBM) The visible units remain classical whereas the hidden units are quantized as noninteracting fermions. This model possesses a quantum behaviour such as coherences between the hidden units.
  arXiv  Detail & Related papers  (2020-01-24T13:38:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.