mlsanityData to 14 Oct 2026

A hybrid quantum-classical approach for inference on restricted Boltzmann machines

arXiv 2304.12418 ↗First posted 31 Mar 2023quant-ph cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Boltzmann machine is a powerful machine learning model with many real-world applications, for example by constructing deep belief networks. Statistical inference on a Boltzmann machine can be carried out by sampling from its posterior distribution. However, uniform sampling from such a model is not trivial due to an extremely multi-modal distribution. Quantum computers have the promise of solving some non-trivial problems in an efficient manner. We explored the application of a D-Wave quantum annealer to generate samples from a restricted Boltzmann machine. The samples are further improved by Markov chains in a hybrid quantum-classical setup. We demonstrated that quantum annealer samples can improve the performance of Gibbs sampling compared to random initialization. The hybrid setup is considerably more efficient than a pure classical sampling. We also investigated the impact of annealing parameters (temperature) to improve the quality of samples. By increasing the amount of classical processing (Gibbs updates) the benefit of quantum annealing vanishes, which may be justified by the limited performance of today's quantum computers compared to classical.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 38 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

16 of 38 references.

References · 16

  1. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  2. 2018Assessing Generative Models via Precision and Recallcited by 406
  3. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  4. 2015Application of Quantum Annealing to Training of Deep Neural Networkscited by 37
  5. 2018Learning and Inference on Generative Adversarial Quantum Circuitscited by 22
  6. 2016Reinforcement Learning Using Quantum Boltzmann Machinescited by 20
  7. 2020Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Qcited by 18
  8. 2019A Path Towards Quantum Advantage in Training Deep Generative Models with Quantum Annealerscited by 15
  9. 2019Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealercited by 7
  10. 2020A Hybrid Quantum enabled RBM Advantage: Convolutional Autoencoders For Quantum Image Compression and Generative Learningcited by 7
  11. 2019Comparison of D-Wave Quantum Annealing and Classical Simulated Annealing for Local Minima Determinationcited by 5
  12. 2020Training a quantum annealing based restricted Boltzmann machine on cybersecurity datacited by 5
4 more
  1. 2021On the challenges of using D-Wave computers to sample Boltzmann Random Variablescited by 4
  2. 2019Towards Sampling from Nondirected Probabilistic Graphical models using a D-Wave Quantum Annealercited by 3
  3. 2020Generative and discriminative training of Boltzmann machine through Quantum annealingcited by 2
  4. 2020Efficient Evaluation of the Partition Function of RBMs with Annealed Importance Samplingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Generalization Bounds in Hybrid Quantum-Classical Machine Learning Modelscited by 3
  2. 2025Comparison of D-Wave Quantum Annealing and Gibbs Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machinecited by 1
  3. 2025Investigation of D-Wave quantum annealing for training Restricted Boltzmann Machines and mitigating catastrophic forgettingcited by 0