Quantum generative adversarial network for generating discrete distribution
Quantum generative adversarial network for generating discrete distribution
复制标题
用于生成离散分布的量子生成对抗网络
DOI：
10.1016/j.ins.2020.05.127
复制
发表时间：
2020-10
影响因子：
8.1
通讯作者：
Zheng Shenggen
中科院分区：
文献类型：
--
作者：
Situ Haozhen;He Zhimin;Wang Yuyi;Li Lvzhou;Zheng Shenggen
量子机器学习最近引起了量子计算界的广泛关注。在本文中，我们探索了基于量子计算的生成对抗网络（GANs）的能力。更具体地说，我们提出了一个量子GAN产生经典离散分布，它具有一个经典-量子混合架构，由一个参数化的量子电路作为发生器和一个经典的神经网络作为控制器。参数化的量子电路仅由简单的单量子比特旋转门和双量子比特相位控制门组成，这在当前的量子器件中是可用的。我们的方案具有以下特点和潜在的优势：（i）它本质上能够生成离散数据（例如，文本数据），而由于梯度消失问题，经典GAN对于这项任务来说很笨拙。(ii)我们的方案避免了现有量子学习算法的输入/输出瓶颈，这些算法要么需要将经典输入数据编码成量子态，要么输出与解对应的量子态，而不是给出解本身，这不可避免地损害了量子算法的加速比。(iii)由数据样本隐式给出的概率分布可以被加载到量子态中，这可能对一些进一步的应用有用。
Quantum machine learning has recently attracted much attention from the community of quantum computing. In this paper, we explore the ability of generative adversarial networks (GANs) based on quantum computing. More specifically, we propose a quantum GAN for generating classical discrete distribution, which has a classical-quantum hybrid architecture and is composed of a parameterized quantum circuit as the generator and a classical neural network as the discriminator. The parameterized quantum circuit only consists of simple one-qubit rotation gates and two-qubit controlled-phase gates that are available in current quantum devices. Our scheme has the following characteristics and potential advantages: (i) It is intrinsically capable of generating discrete data (e.g., text data), while classical GANs are clumsy for this task due to the vanishing gradient problem. (ii) Our scheme avoids the input/output bottlenecks embarrassing most of the existing quantum learning algorithms that either require to encode the classical input data into quantum states, or output a quantum state corresponding to the solution instead of giving the solution itself, which inevitably compromises the speedup of the quantum algorithm. (iii) The probability distribution implicitly given by data samples can be loaded into a quantum state, which may be useful for some further applications.
登录
查看更多内容
影响因子：
8.6
作者：
Monras, Alex;Sentis, Gael;Wittek, Peter
通讯作者：
Wittek, Peter
视觉跟踪的量子算法
影响因子：
2.9
作者：
Yu Chao Hua;Gao Fei;Liu Chenghuan;Du Huynh;Reynolds Mark;Wang Jingbo
通讯作者：
Wang Jingbo
DOI：
10.4018/978-1-5225-9096-5.ch007
发表时间：
2021-07
期刊：
Smart Computational Intelligence in Biomedical and Health Informatics
影响因子：
--
作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
通讯作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
影响因子：
7.6
作者：
Christa Zoufal;Aurélien Lucchi;Stefan Woerner
通讯作者：
Christa Zoufal;Aurélien Lucchi;Stefan Woerner
量子电路 Born 机器的微分学习
影响因子：
2.9
作者：
Liu, Jin-Guo;Wang, Lei
通讯作者：
Wang, Lei