当前位置: X-MOL 学术Mach. Learn. Sci. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A path towards quantum advantage in training deep generative models with quantum annealers
Machine Learning: Science and Technology ( IF 6.3 ) Pub Date : 2020-11-03 , DOI: 10.1088/2632-2153/aba220
Walter Winci 1, 2, 3 , Lorenzo Buffoni 4, 5, 6 , Hossein Sadeghi 4 , Amir Khoshaman 4 , Evgeny Andriyash 4 , Mohammad H Amin 4, 7
Affiliation  

The development of quantum-classical hybrid (QCH) algorithms is critical to achieve state-of-the-art computational models. A QCH variational autoencoder (QVAE) was introduced in reference [1] by some of the authors of this paper. QVAE consists of a classical auto-encoding structure realized by traditional deep neural networks to perform inference to and generation from, a discrete latent space. The latent generative process is formalized as thermal sampling from a quantum Boltzmann machine (QBM). This setup allows quantum-assisted training of deep generative models by physically simulating the generative process with quantum annealers. In this paper, we have successfully employed D-Wave quantum annealers as Boltzmann samplers to perform quantum-assisted, end-to-end training of QVAE. The hybrid structure of QVAE allows us to deploy current-generation quantum annealers in QCH generative models to achieve competitive performance on datasets such as MNIST. The results presented in this paper suggest that commercially available quantum annealers can be deployed, in conjunction with well-crafted classical deep neutral networks, to achieve competitive results in unsupervised and semisupervised tasks on large-scale datasets. We also provide evidence that our setup is able to exploit large latent-space QBMs, which develop slowly mixing modes. This expressive latent space results in slow and inefficient classical sampling and paves the way to achieve quantum advantage with quantum annealing in realistic sampling applications.



中文翻译:

利用量子退火器训练深度生成模型时获得量子优势的途径

量子经典混合(QCH)算法的开发对于实现最新的计算模型至关重要。本文的一些作者在参考文献[1]中介绍了一种QCH可变自动编码器(QVAE)。QVAE由传统的深层神经网络实现的经典自动编码结构组成,可对离散的潜在空间进行推理并从中生成。潜在的生成过程被正式化为来自量子玻尔兹曼机(QBM)的热采样。通过使用量子退火仪物理模拟生成过程,此设置允许对深度生成模型进行量子辅助训练。在本文中,我们已成功地将D-Wave量子退火仪用作Boltzmann采样器来执行QVAE的量子辅助,端到端训练。QVAE的混合结构使我们能够在QCH生成模型中部署当前一代的量子退火器,以在MNIST等数据集上实现竞争性能。本文提出的结果表明,可以将商业上可用的量子退火器与精心设计的经典深层中性网络配合使用,以在大规模数据集的无监督和半监督任务中获得竞争性结果。我们还提供了证据,表明我们的装置能够利用大的潜伏空间QBM,后者会缓慢发展混合模式。这种具有表现力的潜在空间导致缓慢且效率低下的经典采样,并为在实际采样应用中通过量子退火实现量子优势铺平了道路。本文提出的结果表明,可以将商业上可用的量子退火器与精心设计的经典深层中性网络配合使用,以在大规模数据集的无监督和半监督任务中获得竞争性结果。我们还提供了证据,表明我们的装置能够利用大的潜伏空间QBM,后者会缓慢发展混合模式。这种具有表现力的潜在空间导致缓慢且效率低下的经典采样,并为在实际采样应用中通过量子退火实现量子优势铺平了道路。本文提出的结果表明,可以将商业上可用的量子退火器与精心设计的经典深层中性网络配合使用,以在大规模数据集的无监督和半监督任务中获得竞争性结果。我们还提供了证据,表明我们的装置能够利用大的潜在空间QBM,而QBM会缓慢发展混合模式。这种具有表现力的潜在空间导致缓慢且效率低下的经典采样,并为在实际采样应用中通过量子退火实现量子优势铺平了道路。我们还提供了证据,表明我们的装置能够利用大的潜伏空间QBM,后者会缓慢发展混合模式。这种具有表现力的潜在空间导致缓慢且效率低下的经典采样,并为在实际采样应用中通过量子退火实现量子优势铺平了道路。我们还提供了证据,表明我们的装置能够利用大的潜伏空间QBM,后者会缓慢发展混合模式。这种具有表现力的潜在空间导致缓慢且效率低下的经典采样,并为在实际采样应用中通过量子退火实现量子优势铺平了道路。

更新日期:2020-11-03
down
wechat
bug