Differentiable learning of quantum circuit Born machines
Differentiable learning of quantum circuit Born machines
复制标题
量子电路 Born 机器的微分学习
DOI：
10.1103/physreva.98.062324
复制
发表时间：
2018-12-19
影响因子：
2.9
通讯作者：
Wang, Lei
中科院分区：
文献类型：
--
作者：
Liu, Jin-Guo;Wang, Lei
量子电路生成机是一种生成性模型，它将经典数据集的概率分布表示为量子纯态。量子采样问题的计算复杂性考虑表明，与经典神经网络相比，量子电路表现出更强的表达能力。人们可以通过对量子比特的投影测量来有效地从量子电路中提取样本。然而，类似于深度学习中的主要隐式生成模型，如生成性对抗网络，量子电路不能提供生成样本的可能性，这对训练提出了挑战。我们通过最小化核最大平均差异损失，为量子电路生成机器设计了一种高效的基于梯度的学习算法。我们使用深量子电路模拟了条带数据集和高斯混合分布的产生式建模。实验证明了电路深度和基于梯度的优化算法的重要性。所提出的学习算法可以在近期量子器件上运行，并且可以在概率生成建模中显示出量子优势。
Quantum circuit Born machines are generative models which represent the probability distribution of classical dataset as quantum pure states. Computational complexity considerations of the quantum sampling problem suggest that the quantum circuits exhibit stronger expressibility compared to classical neural networks. One can efficiently draw samples from the quantum circuits via projective measurements on qubits. However, similar to the leading implicit generative models in deep learning, such as the generative adversarial networks, the quantum circuits cannot provide the likelihood of the generated samples, which poses a challenge to the training We devise an efficient gradient-based learning algorithm for the quantum circuit Born machine by minimizing the kerneled maximum mean discrepancy loss. We simulated generative modeling of the BARS-AND-STRIPES dataset and Gaussian mixture distributions using deep quantum circuits. Our experiments show the importance of circuit depth and the gradient-based optimization algorithm. The proposed learning algorithm is runnable on near-term quantum device and can exhibit quantum advantages for probabilistic generative modeling.