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

• URL: http://arxiv.org/abs/2304.12418v1
• Date: Fri, 31 Mar 2023 11:10:31 GMT
• Title: A hybrid quantum-classical approach for inference on restricted Boltzmann machines
• Authors: M\=arti\c{n}\v{s} K\=alis, Andris Loc\=ans, Rolands \v{S}ikovs, Hassan Naseri, Andris Ambainis
• Abstract summary: A Boltzmann machine is a powerful machine learning model with many real-world applications. Statistical inference on a Boltzmann machine can be carried out by sampling from its posterior distribution. Quantum computers have the promise of solving some non-trivial problems in an efficient manner.
• Score: 1.0928470926399563
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Non-native Quantum Generative Optimization with Adversarial Autoencoders [34.82692226532414]
  We introduce the adversarial quantum autoencoder model (AQAM) that can be used to map large-scale optimization problems onto existing quantum samplers. We demonstrate that the AQAM achieves a lower Renyi divergence and a larger spectral gap when compared to classical Markov Chain Monte Carlo samplers.
  arXiv  Detail & Related papers  (2024-07-18T18:03:18Z)
• Towards Efficient Quantum Hybrid Diffusion Models [68.43405413443175]
  We propose a new methodology to design quantum hybrid diffusion models. We propose two possible hybridization schemes combining quantum computing's superior generalization with classical networks' modularity.
  arXiv  Detail & Related papers  (2024-02-25T16:57:51Z)
• Iterated Denoising Energy Matching for Sampling from Boltzmann Densities [109.23137009609519]
  Iterated Denoising Energy Matching (iDEM) iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our matching objective. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5times$ faster.
  arXiv  Detail & Related papers  (2024-02-09T01:11:23Z)
• Quantum-Noise-Driven Generative Diffusion Models [1.6385815610837167]
  We propose three quantum-noise-driven generative diffusion models that could be experimentally tested on real quantum systems. The idea is to harness unique quantum features, in particular the non-trivial interplay among coherence, entanglement and noise. Our results are expected to pave the way for new quantum-inspired or quantum-based generative diffusion algorithms.
  arXiv  Detail & Related papers  (2023-08-23T09:09:32Z)
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models [62.997667081978825]
  We build over a proposed framework for evaluating the generalization performance of generative models. We establish the first comparative race towards practical quantum advantage (PQA) between classical and quantum generative models. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models.
  arXiv  Detail & Related papers  (2023-03-27T22:48:28Z)
• Quantum Boltzmann Machines: Applications in Quantitative Finance [0.0]
  We explore using the D-Wave Advantage 4.1 quantum annealer to sample from quantum Boltzmann distributions and train quantum Boltzmann machines (QBMs) Our findings indicate that QBMs trained using the Advantage 4.1 are much noisier than those trained using simulations and struggle to perform at the same level as classical RBMs. There is the potential for QBMs to outperform classical RBMs if future generation annealers can generate samples closer to the desired theoretical distributions.
  arXiv  Detail & Related papers  (2023-01-30T21:25:14Z)
• 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)
• Quantum-enhanced Markov chain Monte Carlo [0.22166578153935784]
  We introduce a quantum algorithm to sample from distributions that pose a bottleneck in several applications. In each step, the quantum processor explores the model in superposition to propose a random move, which is then accepted or rejected by a classical computer. We find that this quantum algorithm converges in fewer iterations than common classical MCMC alternatives on relevant problem instances.
  arXiv  Detail & Related papers  (2022-03-23T15:50:12Z)
• Generalization Metrics for Practical Quantum Advantage in Generative Models [68.8204255655161]
  Generative modeling is a widely accepted natural use case for quantum computers. We construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Our simulation results show that our quantum-inspired models have up to a $68 times$ enhancement in generating unseen unique and valid samples.
  arXiv  Detail & Related papers  (2022-01-21T16:35:35Z)
• Assessment of image generation by quantum annealer [0.0]
  A quantum annealer may also serve as a fast sampler for the Ising spin-glass problem. In this study, we focused on the performance of a quantum annealer as a generative model.
  arXiv  Detail & Related papers  (2021-03-15T13:24:05Z)
• Sampling Overhead Analysis of Quantum Error Mitigation: Uncoded vs. Coded Systems [69.33243249411113]
  We show that Pauli errors incur the lowest sampling overhead among a large class of realistic quantum channels. We conceive a scheme amalgamating QEM with quantum channel coding, and analyse its sampling overhead reduction compared to pure QEM.
  arXiv  Detail & Related papers  (2020-12-15T15:51:27Z)

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.