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

Neural Computation

Determination of the Lowest-Energy States for the Model Distribution of Trained Restricted Boltzmann Machines Using a 1000 Qubit D-Wave 2X Quantum Computer

Yaroslav Koshka, Dilina Perera, Spencer Hall, M. A. Novotny

Published May 31, 2017• 15 citations
Publisher

Abstract

The possibility of using a quantum computer D-Wave 2X with more than 1000 qubits to determine the global minimum of the energy landscape of trained restricted Boltzmann machines is investigated. In order to overcome the problem of limited interconnectivity in the D-Wave architecture, the proposed RBM embedding combines multiple qubits to represent a particular RBM unit. The results for the lowest-energy (the ground state) and some of the higher-energy states found by the D-Wave 2X were compared with those of the classical simulated annealing (SA) algorithm. In many cases, the D-Wave machine successfully found the same RBM lowest-energy state as that found by SA. In some examples, the D-Wave machine returned a state corresponding to one of the higher-energy local minima found by SA. The inherently nonperfect embedding of the RBM into the Chimera lattice explored in this work (i.e., multiple qubits combined into a single RBM unit were found not to be guaranteed to be all aligned) and the existence of small, persistent biases in the D-Wave hardware may cause a discrepancy between the D-Wave and the SA results. In some of the investigated cases, introduction of a small bias field into the energy function or optimization of the chain-strength parameter in the D-Wave embedding successfully addressed difficulties of the particular RBM embedding. With further development of the D-Wave hardware, the approach will be suitable for much larger numbers of RBM units.

DOI
10.1162/neco_a_00974

Related papers

Empirical investigation of the low temperature energy function of the Restricted Boltzmann Machine using a 1000 qubit D-Wave 2X

Yaroslav Koshka, Dilina Perera, Spencer Hall +1 more

D-Wave 2X with more than 1000 qubits was applied to the relatively rugged energy landscape of trained Restricted Boltzmann Machines (RBMs). The D-Wave machine has a Chimera interconnect architecture. A native RBM restricted to the Chimera graph was found difficult to train for large number of RBM units. To overcome this difficulty, a RBM embedding that combined qubits in order to significantly increase the connectivity between hidden and visible units of the RBM was investigated. The results for the lowest-energy and some of the higher-energy states found by D-Wave 2X were compared with those of the classical simulated annealing (SA) algorithm. In many cases, the D-Wave machine successfully found the same RBM lowest energy state as that found by SA. In the relatively simple cases of training patterns investigated in this work, the lowest energy state also corresponded to one of the training patterns. Sometimes the D-Wave machine returned a state corresponding to one of the higher energy states found by SA. The inherently non-perfect embedding of the RBM into the Chimera lattice used in this work (i.e., multiple qubits combined into a single RBM unit were not guaranteed to have perfectly aligned qubits) and the existence of small bias fields in the D-Wave hardware were found to be responsible for the discrepancy in the D-Wave and the SA results. In some but not all of the investigated cases, introduction of a small bias field into the energy function or optimization of the chain-strength parameter in the D-Wave embedding successfully addressed difficulties of the particular RBM embedding.

International Joint Conference on Neural Networks (IJCNN)•Jul 1, 2016•7 citations

2000 Qubit D-Wave Quantum Computer Replacing MCMC for RBM Image Reconstruction and Classification

Yaroslav Koshka, M. A. Novotny

Restricted Boltzmann Machines trained by the classical Contrastive Divergence algorithm were embedded into a next generation D-Wave quantum computer having more than 2000 qubits. The embedding was used to sample missing visible units and labels of incomplete test images. The previously introduced RBM embedding that combined qubits into individual RBM units in order to increase the connectivity between units was used. In comparison to the 1000 qubit machine investigated earlier, the same embedding approach applied to the 2000 qubit D-Wave enabled a connectivity between RBM units sufficient for RBM training on a classical computer with a satisfactory classification error. After a varied number of CD training iterations, the visible units corresponding to a particular incomplete test image were fixed in the D-Wave embedding. The resulting state returned by the D-Wave represents the most energetically favorable combination of the remaining qubits for the given fixed incomplete input image. The classification errors compared favorably to those obtained by the classical MCMC sampling. Main factors influencing the quality of the embedding were investigated. Regardless of the computational cost incentives for using the D-Wave for this operation, the reconstruction and classification errors determined in this way can be used at least as a verification of the validity and quality of the particular embedding of the given RBM architecture. This is essential for successfully employing a QC in much more computationally demanding parts of the RBM training. opportunities for using QC not only for recognition but especially for RBM training, in particular for obtaining a representative sample from the RBM model distribution, are discussed.

International Joint Conference on Neural Networks (IJCNN)•Jul 1, 2018•5 citations

Comparison of Use of a 2000 Qubit D-Wave Quantum Annealer and MCMC for Sampling, Image Reconstruction, and Classification

Yaroslav Koshka, M. A. Novotny

The next generation D-Wave quantum computer (QC) having more than 2000 qubits was demonstrated to be adequate for embedding graphs of restricted Boltzmann machines (RBMs) having the connectivity between RBM units (though still limited) already sufficient for successful training by classical algorithms. As a verification of the validity and quality of the employed embedding approach, the RBM was trained by classical contrastive divergence (CD), while the D-Wave was initially used only in the recognition step for reconstruction of incomplete test images (8 × 8 bars-and-stripes), and for their classification. The label classification errors by the D-Wave compared favorably to those obtained by classical Gibbs sampling, indicating that the QC was successfully finding the most energetically favorable combinations of the unknown visible RBM units/labels for the given fixed incomplete input image. The valid RBM embedding was further applied to investigate opportunities for using QCs in the RBM training, and specifically for replacing the classical Gibbs technique in generating a representative sample from the RBM model distribution. Statistical comparison of samples obtained by the Gibbs technique versus 10000 sample states generated from the D-Wave revealed significant differences in the observed outcomes. The D-Wave samples were found insufficiently representative of the model distribution, specifically by missing many local valley found by the Gibbs sampling. On the other hand, the D-Wave possessed an ability to find local valleys of the configuration space that were consistently missed by the classical sampling algorithms, which could potentially be very interesting for sampling applications.

IEEE Transactions on Emerging Topics in Computational Intelligence•Oct 2, 2018•16 citations

Comparison of quantum and classical methods for labels and patterns in Restricted Boltzmann Machines

Vivek Dixit, Yaroslav Koshka, Tamer Aldwairi +1 more

Abstract Classification and data reconstruction using a restricted Boltzmann machine (RBM) is presented. RBM is an energy-based model which assigns low energy values to the configurations of interest. It is a generative model, once trained it can be used to produce samples from the target distribution. The D-Wave 2000Q is a quantum computer which has been used to exploit its quantum effect for machine learning. Bars-and-stripes (BAS) and cybersecurity (ISCX) datasets were used to train RBMs. The weights and biases of trained RBMs were used to map onto the D-Wave. Classification as well as image reconstruction were performed. Classification accuracy of both datasets indicates comparable performance using D-Wave’s adiabatic annealing and classical Gibb’s sampling.

Journal of Physics Conference Series•Nov 1, 2021•6 citations

Comparison of D-Wave Quantum Annealing and Gibbs Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machine

Abdelmoula El-Yazizi, Yaroslav Koshka

A local-valley (LV)-centered approach to assessing the quality of sampling from Restricted Boltzmann Machines (RBMs) was applied to the latest generation of the D-Wave quantum annealer. D-Wave and Gibbs samples from a classically trained RBM were obtained at conditions relevant to contrastive-divergence-based RBM learning. The samples were compared for the number of LVs to which they belonged and the energy of the corresponding local minima. No significant (desirable) increase in the number of the LVs has been achieved by decreasing the D-Wave annealing time. At any training epoch, the states sampled by the D-Wave belonged to a somewhat higher number of LVs than in the Gibbs sampling. However, many of those LVs found by the two techniques differed. For high-probability sampled states, the two techniques were (unfavorably) less complementary and more overlapping. Nevertheless, many potentially "important" local minima, i.e., those having intermediate, even if not high, probability values, were found by only one of the two sampling techniques while missed by the other. The two techniques overlapped less at later than earlier training epochs, which is precisely the stage of the training when modest improvements to the sampling quality could make meaningful differences for the RBM trainability. The results of this work may explain the failure of previous investigations to achieve substantial (or any) improvement when using D-Wave-based sampling. However, the results reveal some potential for improvement, e.g., using a combined classical-quantum approach.

arXiv:2508.10228•Entropy•Aug 18, 2026•1 citation

Generating Sparse Representations Using Quantum Annealing: Comparison to Classical Algorithms

Nga T. T. Nguyen, Amy E. Larson, Garrett T. Kenyon

We use a quantum annealing D-Wave 2X (1,152-qubit) computer to generate sparse representations of Canny-filtered, center-cropped 30×30 CIFAR-10 images. Each binary neuron (qubit) represents a feature kernel obtained initially by imprinting on a randomly chosen 5×5 image patch and then adapted via an off-line Hebbian learning protocol using the sparse solutions generated by the D-Wave. When using binary neurons, the energy function is non-convex (multiple local-minima) and finding a global minimum is NP-hard. Quantum annealing provides a strategy for finding sparse representations that correspond to good local minima of a non-convex cost function. To overcome the severe coupling restrictions between physical qubits on the D-Wave Chimera graph, we use embedding tools to achieve approximately all-to-all connectivity across a reduced number of logical qubits. We assess the sparse representations generated by the D-Wave using both the total energy as well as classification accuracy on a subset of the CIFAR-10 database. The D-Wave 2X outperforms two classical state-of-the-art binary solvers, GUROBI and Chimera-inspired algorithm Hamze-Freitas-Selby (HFS). Specifically, the D-Wave 2X yields lower energy sparse solutions within seconds while the largest problems take over 10 hours for both GUROBI and HFS. We obtained cross-validation classification of 31.02% for the first 4K images using 47 features on the quantum D- Wave 2X.

IEEE International Conference on Rebooting Computing (ICRC)•Nov 1, 2017•7 citations
The possibility of using a quantum computer D-Wave 2X with more than 1000 qubits to determine the global minimum of the energy landscape of trained restricted Boltzmann machines is investigated. In order to overcome the problem of limited interconnectivity in the D-Wave architecture, the proposed RBM embedding combines multiple qubits to represent a particular RBM unit. The results for the lowest-energy (the ground state) and some of the higher-energy states found by the D-Wave 2X were compared with those of the classical simulated annealing (SA) algorithm. In many cases, the D-Wave machine successfully found the same RBM lowest-energy state as that found by SA. In some examples, the D-Wave machine returned a state corresponding to one of the higher-energy local minima found by SA. The inherently nonperfect embedding of the RBM into the Chimera lattice explored in this work (i.e., multiple qubits combined into a single RBM unit were found not to be guaranteed to be all aligned) and the existence of small, persistent biases in the D-Wave hardware may cause a discrepancy between the D-Wave and the SA results. In some of the investigated cases, introduction of a small bias field into the energy function or optimization of the chain-strength parameter in the D-Wave embedding successfully addressed difficulties of the particular RBM embedding. With further development of the D-Wave hardware, the approach will be suitable for much larger numbers of RBM units.
D-Wave 2X with more than 1000 qubits was applied to the relatively rugged energy landscape of trained Restricted Boltzmann Machines (RBMs). The D-Wave machine has a Chimera interconnect architecture. A native RBM restricted to the Chimera graph was found difficult to train for large number of RBM units. To overcome this difficulty, a RBM embedding that combined qubits in order to significantly increase the connectivity between hidden and visible units of the RBM was investigated. The results for the lowest-energy and some of the higher-energy states found by D-Wave 2X were compared with those of the classical simulated annealing (SA) algorithm. In many cases, the D-Wave machine successfully found the same RBM lowest energy state as that found by SA. In the relatively simple cases of training patterns investigated in this work, the lowest energy state also corresponded to one of the training patterns. Sometimes the D-Wave machine returned a state corresponding to one of the higher energy states found by SA. The inherently non-perfect embedding of the RBM into the Chimera lattice used in this work (i.e., multiple qubits combined into a single RBM unit were not guaranteed to have perfectly aligned qubits) and the existence of small bias fields in the D-Wave hardware were found to be responsible for the discrepancy in the D-Wave and the SA results. In some but not all of the investigated cases, introduction of a small bias field into the energy function or optimization of the chain-strength parameter in the D-Wave embedding successfully addressed difficulties of the particular RBM embedding.
Restricted Boltzmann Machines trained by the classical Contrastive Divergence algorithm were embedded into a next generation D-Wave quantum computer having more than 2000 qubits. The embedding was used to sample missing visible units and labels of incomplete test images. The previously introduced RBM embedding that combined qubits into individual RBM units in order to increase the connectivity between units was used. In comparison to the 1000 qubit machine investigated earlier, the same embedding approach applied to the 2000 qubit D-Wave enabled a connectivity between RBM units sufficient for RBM training on a classical computer with a satisfactory classification error. After a varied number of CD training iterations, the visible units corresponding to a particular incomplete test image were fixed in the D-Wave embedding. The resulting state returned by the D-Wave represents the most energetically favorable combination of the remaining qubits for the given fixed incomplete input image. The classification errors compared favorably to those obtained by the classical MCMC sampling. Main factors influencing the quality of the embedding were investigated. Regardless of the computational cost incentives for using the D-Wave for this operation, the reconstruction and classification errors determined in this way can be used at least as a verification of the validity and quality of the particular embedding of the given RBM architecture. This is essential for successfully employing a QC in much more computationally demanding parts of the RBM training. opportunities for using QC not only for recognition but especially for RBM training, in particular for obtaining a representative sample from the RBM model distribution, are discussed.
The next generation D-Wave quantum computer (QC) having more than 2000 qubits was demonstrated to be adequate for embedding graphs of restricted Boltzmann machines (RBMs) having the connectivity between RBM units (though still limited) already sufficient for successful training by classical algorithms. As a verification of the validity and quality of the employed embedding approach, the RBM was trained by classical contrastive divergence (CD), while the D-Wave was initially used only in the recognition step for reconstruction of incomplete test images (8 × 8 bars-and-stripes), and for their classification. The label classification errors by the D-Wave compared favorably to those obtained by classical Gibbs sampling, indicating that the QC was successfully finding the most energetically favorable combinations of the unknown visible RBM units/labels for the given fixed incomplete input image. The valid RBM embedding was further applied to investigate opportunities for using QCs in the RBM training, and specifically for replacing the classical Gibbs technique in generating a representative sample from the RBM model distribution. Statistical comparison of samples obtained by the Gibbs technique versus 10000 sample states generated from the D-Wave revealed significant differences in the observed outcomes. The D-Wave samples were found insufficiently representative of the model distribution, specifically by missing many local valley found by the Gibbs sampling. On the other hand, the D-Wave possessed an ability to find local valleys of the configuration space that were consistently missed by the classical sampling algorithms, which could potentially be very interesting for sampling applications.
Abstract Classification and data reconstruction using a restricted Boltzmann machine (RBM) is presented. RBM is an energy-based model which assigns low energy values to the configurations of interest. It is a generative model, once trained it can be used to produce samples from the target distribution. The D-Wave 2000Q is a quantum computer which has been used to exploit its quantum effect for machine learning. Bars-and-stripes (BAS) and cybersecurity (ISCX) datasets were used to train RBMs. The weights and biases of trained RBMs were used to map onto the D-Wave. Classification as well as image reconstruction were performed. Classification accuracy of both datasets indicates comparable performance using D-Wave’s adiabatic annealing and classical Gibb’s sampling.
A local-valley (LV)-centered approach to assessing the quality of sampling from Restricted Boltzmann Machines (RBMs) was applied to the latest generation of the D-Wave quantum annealer. D-Wave and Gibbs samples from a classically trained RBM were obtained at conditions relevant to contrastive-divergence-based RBM learning. The samples were compared for the number of LVs to which they belonged and the energy of the corresponding local minima. No significant (desirable) increase in the number of the LVs has been achieved by decreasing the D-Wave annealing time. At any training epoch, the states sampled by the D-Wave belonged to a somewhat higher number of LVs than in the Gibbs sampling. However, many of those LVs found by the two techniques differed. For high-probability sampled states, the two techniques were (unfavorably) less complementary and more overlapping. Nevertheless, many potentially "important" local minima, i.e., those having intermediate, even if not high, probability values, were found by only one of the two sampling techniques while missed by the other. The two techniques overlapped less at later than earlier training epochs, which is precisely the stage of the training when modest improvements to the sampling quality could make meaningful differences for the RBM trainability. The results of this work may explain the failure of previous investigations to achieve substantial (or any) improvement when using D-Wave-based sampling. However, the results reveal some potential for improvement, e.g., using a combined classical-quantum approach.
We use a quantum annealing D-Wave 2X (1,152-qubit) computer to generate sparse representations of Canny-filtered, center-cropped 30×30 CIFAR-10 images. Each binary neuron (qubit) represents a feature kernel obtained initially by imprinting on a randomly chosen 5×5 image patch and then adapted via an off-line Hebbian learning protocol using the sparse solutions generated by the D-Wave. When using binary neurons, the energy function is non-convex (multiple local-minima) and finding a global minimum is NP-hard. Quantum annealing provides a strategy for finding sparse representations that correspond to good local minima of a non-convex cost function. To overcome the severe coupling restrictions between physical qubits on the D-Wave Chimera graph, we use embedding tools to achieve approximately all-to-all connectivity across a reduced number of logical qubits. We assess the sparse representations generated by the D-Wave using both the total energy as well as classification accuracy on a subset of the CIFAR-10 database. The D-Wave 2X outperforms two classical state-of-the-art binary solvers, GUROBI and Chimera-inspired algorithm Hamze-Freitas-Selby (HFS). Specifically, the D-Wave 2X yields lower energy sparse solutions within seconds while the largest problems take over 10 hours for both GUROBI and HFS. We obtained cross-validation classification of 31.02% for the first 4K images using 47 features on the quantum D- Wave 2X.