当前位置: X-MOL 学术Quantum 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.)
Characterizing the loss landscape of variational quantum circuits
Quantum Science and Technology ( IF 6.7 ) Pub Date : 2021-02-20 , DOI: 10.1088/2058-9565/abdbc9
Patrick Huembeli , Alexandre Dauphin

Machine learning techniques enhanced by noisy intermediate-scale quantum (NISQ) devices and especially variational quantum circuits (VQC) have recently attracted much interest and have already been benchmarked for certain problems. Inspired by classical deep learning, VQCs are trained by gradient descent methods which allow for efficient training over big parameter spaces. For NISQ sized circuits, such methods show good convergence. There are however still many open questions related to the convergence of the loss function and to the trainability of these circuits in situations of vanishing gradients. Furthermore, it is not clear how ‘good’ the minima are in terms of generalization and stability against perturbations of the data and there is, therefore, a need for tools to quantitatively study the convergence of the VQCs. In this work, we introduce a way to compute the Hessian of the loss function of VQCs and show how to characterize the loss landscape with it. The eigenvalues of the Hessian give information on the local curvature and we discuss how this information can be interpreted and compared to classical neural networks. We benchmark our results on several examples, starting with a simple analytic toy model to provide some intuition about the behaviour of the Hessian, then going to bigger circuits, and also train VQCs on data. Finally, we show how the Hessian can be used to adjust the learning rate for faster convergence during the training of variational circuits.



中文翻译:

表征变分量子电路的损耗态势

嘈杂的中级量子(NISQ)设备,尤其是变分量子电路(VQC)增强了机器学习技术,近来引起了人们的极大兴趣,并且已经针对某些问题进行了基准测试。受到经典深度学习的启发,VQC通过梯度下降方法进行训练,从而可以在大参数空间上进行有效的训练。对于NISQ大小的电路,此类方法显示出良好的收敛性。但是,仍然存在许多与损耗函数的收敛性以及在梯度消失的情况下这些电路的可训练性有关的悬而未决的问题。此外,尚不清楚最小值在泛化和针对数据扰动的稳定性方面有多“好”,因此,需要一种工具来定量研究VQC的收敛性。在这项工作中,我们介绍了一种计算VQC损失函数的Hessian的方法,并展示了如何用它来描述损失情况。Hessian的特征值提供有关局部曲率的信息,我们讨论了如何解释这些信息并将其与经典神经网络进行比较。我们以几个示例为基准对我们的结果进行基准测试,首先从一个简单的分析玩具模型开始,以提供有关Hessian行为的一些直觉,然后进入更大的电路,并对VQC进行数据训练。最后,我们展示了如何在训练可变电路的过程中使用Hessian来调整学习速率,以便更快地收敛。Hessian的特征值提供有关局部曲率的信息,我们讨论了如何解释这些信息并将其与经典神经网络进行比较。我们以几个示例为基准对我们的结果进行基准测试,首先从一个简单的分析玩具模型开始,以提供有关Hessian行为的一些直觉,然后进入更大的电路,并对VQC进行数据训练。最后,我们展示了如何在训练可变电路的过程中使用Hessian来调整学习速率,以便更快地收敛。Hessian的特征值提供有关局部曲率的信息,我们讨论了如何解释这些信息并将其与经典神经网络进行比较。我们以几个示例为基准对我们的结果进行基准测试,首先从一个简单的分析玩具模型开始,以提供有关Hessian行为的一些直觉,然后进入更大的电路,并对VQC进行数据训练。最后,我们展示了如何在训练可变电路的过程中使用Hessian来调整学习速率,以便更快地收敛。

更新日期:2021-02-20
down
wechat
bug