Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Japanese Journal of Applied Physics

Method for Determining Weight Coefficients for Quantum Boltzmann Machine Neuron Devices

Nanjian Wu, Hassu Lee, Yoshihito Amemiya, Hitoshi Yasunaga

Published Jan 1, 1999• 1 citation
Publisher

Abstract

A method for designing weight coefficients in the quantum Boltzmann machine (QBM) neuron device is proposed. The exchange interaction coefficient corresponds to the weight coefficient of the QBM neuron. A quantitative clarification of the dependence of the exchange interaction coefficient on two physical factors is given: the interval and the barrier height between the nearest-neighbor dots. It is demonstrated that the weight coefficient of the QBM neuron device can be controlled by specifying the values for these two physical factors during the design phase.

DOI
10.1143/jjap.38.439

Related papers

Boltzmann machine neuron device using quantum-coupled single electrons

Nanjian Wu, Naoto Shibata, Yoshihito Amemiya

A quantum Boltzmann machine (QBM) neuron device is proposed. It consists of a two-dimensional (2D) arrangement of quantum dots that is occupied by quantum-coupled single electrons. The two possible polarizations, “down” and “up,” of the electron spin are used to encode the binary states 0 and 1. The QBM neuron device produces stochastic operations naturally because the electron spin takes the polarization down or up with a certain probability. Calculations for the operation of the QBM neuron device are presented and it is demonstrated that the device can perform the stochastic operations of the BM neuron.

Applied Physics Letters•Jun 15, 1998•9 citations

On the sample complexity of quantum Boltzmann machine learning

Luuk Coopmans, Marcello Benedetti

Abstract Quantum Boltzmann machines (QBMs) are machine-learning models for both classical and quantum data. We give an operational definition of QBM learning in terms of the difference in expectation values between the model and target, taking into account the polynomial size of the data set. By using the relative entropy as a loss function, this problem can be solved without encountering barren plateaus. We prove that a solution can be obtained with stochastic gradient descent using at most a polynomial number of Gibbs states. We also prove that pre-training on a subset of the QBM parameters can only lower the sample complexity bounds. In particular, we give pre-training strategies based on mean-field, Gaussian Fermionic, and geometrically local Hamiltonians. We verify these models and our theoretical findings numerically on a quantum and a classical data set. Our results establish that QBMs are promising machine learning models.

arXiv:2306.14969•Communications Physics•Aug 14, 2024•27 citations

Quantum Boltzmann machine algorithm with dimension-expanded equivalent Hamiltonian

Tailong Xiao, Dongyun Bai, Jianping Fan B +1 more

Quantum machine learning explores the devising and implementing of quantum software to enable the speedup for a classical machine learning counterpart, which has attracted extensive attention. The quantum Boltzmann machine is a promising quantum machine learning model and can be executed on near-term quantum devices to demonstrate quantum supremacy. We investigate an efficient algorithm for training a quantum Boltzmann machine based on a continuous-time quantum cluster Monte Carlo method realized with a dimension-expanded equivalent Hamiltonian. The proposed algorithm is capable of efficiently training various types of quantum Boltzmann machines, including a two-dimensional random transverse Ising Hamiltonian and other stochastic $\ensuremath{\kappa}$-local $(\ensuremath{\kappa}\ensuremath{\ge}2)$ Hamiltonians. We further apply a quantum mean-field method to speed up the training process through discarding the quantum fluctuations of visible-hidden interactions. The experiment results show that our algorithm-trained quantum Boltzmann machine is more efficient on a small and large data set in terms of network convergence and time complexity.

Physical Review A•Mar 5, 2020•13 citations

Realizing number recognition with simulated quantum semi-restricted Boltzmann machine

Fu-Wen Zhang, Yong-Gang Tan, Qing-yu Cai

Abstract Quantum machine learning based on quantum algorithms may achieve an exponential speedup over classical algorithms in dealing with some problems such as clustering. In this paper, we use the method of training the lower bound of the average log likelihood function on the quantum Boltzmann machine (QBM) to recognize the handwritten number datasets and compare the training results with classical models. We find that, when the QBM is semi-restricted, the training results get better with fewer computing resources. This shows that it is necessary to design a targeted algorithm to speed up computation and save resources.

Communications in Theoretical Physics•May 16, 2022•0 citations

Training quantum Boltzmann machines with the β-variational quantum eigensolver

Onno Huijgen, Luuk Coopmans, Peyman Najafi +2 more

Abstract The quantum Boltzmann machine (QBM) is a generative machine learning model for both classical data and quantum states. Training the QBM consists of minimizing the relative entropy from the model to the target state. This requires QBM expectation values which are computationally intractable for large models in general. It is therefore important to develop heuristic training methods that work well in practice. In this work, we study a heuristic method characterized by a nested loop: the inner loop trains the β-variational quantum eigensolver (β-VQE) by Liu et al (2021 Mach. Learn.: Sci. Technol. 2 025011) to approximate the QBM expectation values; the outer loop trains the QBM to minimize the relative entropy to the target. We show that low-rank representations obtained by β-VQE provide an efficient way to learn low-rank target states, such as classical data and low-temperature quantum tomography. We test the method on both classical and quantum target data with numerical simulations of up to 10 qubits. For the cases considered here, the obtained QBMs can model the target to high fidelity. We implement a trained model on a physical quantum device. The approach offers a valuable route towards variationally training QBMs on near-term quantum devices.

arXiv:2304.08631•Machine Learning Science and Technology•Mar 22, 2024•8 citations

Variational quantum Boltzmann machines

Christa Zoufal, Aurélien Lucchi, Stefan Woerner

Abstract This work presents a novel realization approach to quantum Boltzmann machines (QBMs). The preparation of the required Gibbs states, as well as the evaluation of the loss function’s analytic gradient, is based on variational quantum imaginary time evolution, a technique that is typically used for ground-state computation. In contrast to existing methods, this implementation facilitates near-term compatible QBM training with gradients of the actual loss function for arbitrary parameterized Hamiltonians which do not necessarily have to be fully visible but may also include hidden units. The variational Gibbs state approximation is demonstrated with numerical simulations and experiments run on real quantum hardware provided by IBM Quantum. Furthermore, we illustrate the application of this variational QBM approach to generative and discriminative learning tasks using numerical simulation.

arXiv:2006.06004•Quantum Machine Intelligence•Feb 22, 2021•99 citations
A method for designing weight coefficients in the quantum Boltzmann machine (QBM) neuron device is proposed. The exchange interaction coefficient corresponds to the weight coefficient of the QBM neuron. A quantitative clarification of the dependence of the exchange interaction coefficient on two physical factors is given: the interval and the barrier height between the nearest-neighbor dots. It is demonstrated that the weight coefficient of the QBM neuron device can be controlled by specifying the values for these two physical factors during the design phase.
A quantum Boltzmann machine (QBM) neuron device is proposed. It consists of a two-dimensional (2D) arrangement of quantum dots that is occupied by quantum-coupled single electrons. The two possible polarizations, “down” and “up,” of the electron spin are used to encode the binary states 0 and 1. The QBM neuron device produces stochastic operations naturally because the electron spin takes the polarization down or up with a certain probability. Calculations for the operation of the QBM neuron device are presented and it is demonstrated that the device can perform the stochastic operations of the BM neuron.
Abstract Quantum Boltzmann machines (QBMs) are machine-learning models for both classical and quantum data. We give an operational definition of QBM learning in terms of the difference in expectation values between the model and target, taking into account the polynomial size of the data set. By using the relative entropy as a loss function, this problem can be solved without encountering barren plateaus. We prove that a solution can be obtained with stochastic gradient descent using at most a polynomial number of Gibbs states. We also prove that pre-training on a subset of the QBM parameters can only lower the sample complexity bounds. In particular, we give pre-training strategies based on mean-field, Gaussian Fermionic, and geometrically local Hamiltonians. We verify these models and our theoretical findings numerically on a quantum and a classical data set. Our results establish that QBMs are promising machine learning models.
Quantum machine learning explores the devising and implementing of quantum software to enable the speedup for a classical machine learning counterpart, which has attracted extensive attention. The quantum Boltzmann machine is a promising quantum machine learning model and can be executed on near-term quantum devices to demonstrate quantum supremacy. We investigate an efficient algorithm for training a quantum Boltzmann machine based on a continuous-time quantum cluster Monte Carlo method realized with a dimension-expanded equivalent Hamiltonian. The proposed algorithm is capable of efficiently training various types of quantum Boltzmann machines, including a two-dimensional random transverse Ising Hamiltonian and other stochastic $\ensuremath{\kappa}$-local $(\ensuremath{\kappa}\ensuremath{\ge}2)$ Hamiltonians. We further apply a quantum mean-field method to speed up the training process through discarding the quantum fluctuations of visible-hidden interactions. The experiment results show that our algorithm-trained quantum Boltzmann machine is more efficient on a small and large data set in terms of network convergence and time complexity.
Abstract Quantum machine learning based on quantum algorithms may achieve an exponential speedup over classical algorithms in dealing with some problems such as clustering. In this paper, we use the method of training the lower bound of the average log likelihood function on the quantum Boltzmann machine (QBM) to recognize the handwritten number datasets and compare the training results with classical models. We find that, when the QBM is semi-restricted, the training results get better with fewer computing resources. This shows that it is necessary to design a targeted algorithm to speed up computation and save resources.
Abstract The quantum Boltzmann machine (QBM) is a generative machine learning model for both classical data and quantum states. Training the QBM consists of minimizing the relative entropy from the model to the target state. This requires QBM expectation values which are computationally intractable for large models in general. It is therefore important to develop heuristic training methods that work well in practice. In this work, we study a heuristic method characterized by a nested loop: the inner loop trains the β-variational quantum eigensolver (β-VQE) by Liu et al (2021 Mach. Learn.: Sci. Technol. 2 025011) to approximate the QBM expectation values; the outer loop trains the QBM to minimize the relative entropy to the target. We show that low-rank representations obtained by β-VQE provide an efficient way to learn low-rank target states, such as classical data and low-temperature quantum tomography. We test the method on both classical and quantum target data with numerical simulations of up to 10 qubits. For the cases considered here, the obtained QBMs can model the target to high fidelity. We implement a trained model on a physical quantum device. The approach offers a valuable route towards variationally training QBMs on near-term quantum devices.
Abstract This work presents a novel realization approach to quantum Boltzmann machines (QBMs). The preparation of the required Gibbs states, as well as the evaluation of the loss function’s analytic gradient, is based on variational quantum imaginary time evolution, a technique that is typically used for ground-state computation. In contrast to existing methods, this implementation facilitates near-term compatible QBM training with gradients of the actual loss function for arbitrary parameterized Hamiltonians which do not necessarily have to be fully visible but may also include hidden units. The variational Gibbs state approximation is demonstrated with numerical simulations and experiments run on real quantum hardware provided by IBM Quantum. Furthermore, we illustrate the application of this variational QBM approach to generative and discriminative learning tasks using numerical simulation.