Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines

• URL: http://arxiv.org/abs/2410.16363v1
• Date: Mon, 21 Oct 2024 18:00:01 GMT
• Title: Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines
• Authors: Cenk Tüysüz, Maria Demidik, Luuk Coopmans, Enrico Rinaldi, Vincent Croft, Yacine Haddad, Matthias Rosenkranz, Karl Jansen,
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, researchers have been exploring ways to generalize Boltzmann machines (BMs) to quantum systems, leading to the development of variations such as fully-visible and restricted quantum Boltzmann machines (QBMs). Due to the non-commuting nature of their Hamiltonians, restricted QBMs face trainability issues, whereas fully-visible QBMs have emerged as a more tractable option, as recent results demonstrate their sample-efficient trainability. These results position fully-visible QBMs as a favorable choice, offering potential improvements over fully-visible BMs without suffering from the trainability issues associated with restricted QBMs. In this work, we show that low-dimensional, fully-visible QBMs can learn to generate distributions typically associated with higher-dimensional systems. We validate our findings through numerical experiments on both artificial datasets and real-world examples from the high energy physics problem of jet event generation. We find that non-commuting terms and Hamiltonian connectivity improve the learning capabilities of QBMs, providing flexible resources suitable for various hardware architectures. Furthermore, we provide strategies and future directions to maximize the learning capacity of fully-visible QBMs.

Related papers

• Expressive equivalence of classical and quantum restricted Boltzmann machines [1.1639171061272031]
  We propose a semi-quantum restricted Boltzmann machine (sqRBM) for classical data. sqRBM is commuting in the visible subspace while remaining non-commuting in the hidden subspace. Our theoretical analysis predicts that, to learn a given probability distribution, an RBM requires three times as many hidden units as an sqRBM.
  arXiv  Detail & Related papers  (2025-02-24T19:00:02Z)
• State estimation with quantum extreme learning machines beyond the scrambling time [0.0]
  We show efficient state estimation is possible even beyond the scrambling time, for many different types of dynamics. These results offer promising venues for robust experimental QELM-based state estimation protocols.
  arXiv  Detail & Related papers  (2024-09-10T18:00:06Z)
• Requirements for building effective Hamiltonians using quantum-enhanced density matrix downfolding [0.0]
  Density matrix downfolding (DMD) is a technique for regressing low-energy effective Hamiltonians from quantum many-body Hamiltonians. One limiting factor in the accuracy of classical implementations of DMD is the presence of difficult-to-quantify systematic errors. We propose a hybrid quantum-classical protocol for circumventing this limitation.
  arXiv  Detail & Related papers  (2024-03-02T00:27:18Z)
• GQHAN: A Grover-inspired Quantum Hard Attention Network [53.96779043113156]
  Grover-inspired Quantum Hard Attention Mechanism (GQHAM) is proposed. GQHAN adeptly surmounts the non-differentiability hurdle, surpassing the efficacy of extant quantum soft self-attention mechanisms. The proposal of GQHAN lays the foundation for future quantum computers to process large-scale data, and promotes the development of quantum computer vision.
  arXiv  Detail & Related papers  (2024-01-25T11:11:16Z)
• QKSAN: A Quantum Kernel Self-Attention Network [53.96779043113156]
  A Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. A Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques. Four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST.
  arXiv  Detail & Related papers  (2023-08-25T15:08:19Z)
• 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. We prove that a solution can be obtained with gradient descent using at most a number of Gibbs states. 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)
• TeD-Q: a tensor network enhanced distributed hybrid quantum machine learning framework [59.07246314484875]
  TeD-Q is an open-source software framework for quantum machine learning. It seamlessly integrates classical machine learning libraries with quantum simulators. It provides a graphical mode in which the quantum circuit and the training progress can be visualized in real-time.
  arXiv  Detail & Related papers  (2023-01-13T09:35:05Z)
• Potential and limitations of quantum extreme learning machines [55.41644538483948]
  We present a framework to model QRCs and QELMs, showing that they can be concisely described via single effective measurements. Our analysis paves the way to a more thorough understanding of the capabilities and limitations of both QELMs and QRCs.
  arXiv  Detail & Related papers  (2022-10-03T09:32:28Z)
• QSAN: A Near-term Achievable Quantum Self-Attention Network [73.15524926159702]
  Self-Attention Mechanism (SAM) is good at capturing the internal connections of features. A novel Quantum Self-Attention Network (QSAN) is proposed for image classification tasks on near-term quantum devices.
  arXiv  Detail & Related papers  (2022-07-14T12:22:51Z)
• 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)
• Entanglement transfer, accumulation and retrieval via quantum-walk-based qubit-qudit dynamics [50.591267188664666]
  Generation and control of quantum correlations in high-dimensional systems is a major challenge in the present landscape of quantum technologies. We propose a protocol that is able to attain entangled states of $d$-dimensional systems through a quantum-walk-based it transfer & accumulate mechanism. In particular, we illustrate a possible photonic implementation where the information is encoded in the orbital angular momentum and polarization degrees of freedom of single photons.
  arXiv  Detail & Related papers  (2020-10-14T14:33:34Z)

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.