Non-Differentiable Learning of Quantum Circuit Born Machine with Genetic Algorithm
Non-Differentiable Learning of Quantum Circuit Born Machine with Genetic Algorithm
复制标题
DOI：
10.2139/ssrn.3569226
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
A. Kondratyev
中科院分区：
文献类型：
--
作者：
A. Kondratyev
量子电路出生机器（QCBM）是一种生成式量子机器学习模型，可以在NISQ时代的量子处理器上有效地训练和运行。QCBM具有比经典神经网络（如受限玻尔兹曼机（RBM））更强的表达能力，因此，QCBM有潜力通过从学习的经验分布中生成高质量的样本来展示量子优势，同时使用比经典神经网络更少的计算资源。然而，如何有效地训练质量信任模型仍然是一个具有挑战性的问题。当损失函数高度非光滑时，传统的可微学习方法可能无法很好地工作。在这种情况下，使用不可微学习方法可能会更有效。提出了一种基于遗传算法的QCBM不可微学习训练方法。本文还给出了用遗传算法训练的QCBM与等效经典RBM性能的数值实验结果，并探讨了遗传算法的收敛性作为QCBM结构的函数以及算法超参数的选择问题。
The Quantum Circuit Born Machine (QCBM) is a generative quantum machine learning model that can be efficiently trained and run on the NISQ era quantum processors. QCBM has greater expressive power than comparable classical neural networks such as Restricted Boltzmann Machine (RBM) and, therefore, has potential to demonstrate quantum advantage by generating high quality samples from the learned empirical distribution while using less computational resources than its classical counterpart. However, efficient training of QCBM remains a challenging problem. Traditional differentiable learning approach may not work well when the loss function is highly non-smooth. In such cases it may be more efficient to use the non-differentiable learning methods. This paper proposes a non-differentiable learning approach to the training of QCBM based on Genetic Algorithm (GA). The paper also presents results of the numerical experiments which compare performance of QCBM trained with GA against performance of the equivalent classical RBM and investigates the question of GA convergence as a function of QCBM architecture and the choice of algorithm’s hyperparameters.