arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09376quant-phcs.LG
收藏

通过高斯初始化摆脱深度变分量子电路中的贫瘠高原

Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits

School of Computer Science, Faculty of Engineering, The University of Sydney(悉尼大学工程学院计算机科学学院)

Kaining Zhang, Liu Liu, Min-Hsiu Hsieh, Dacheng Tao

AI总结:

针对深度变分量子电路的梯度指数消失问题,本文提出带理论保证的高斯初始化策略,证明梯度范数至多多项式衰减,并通过量子模拟与量子化学实验验证。

摘要:

近年来,变分量子电路已被广泛应用于量子模拟和量子机器学习。然而,具有随机结构的量子电路由于梯度相对于电路深度和量子比特数呈指数级消失,其可训练性较差。这一结果导致了一种普遍观点,即深度量子电路在实际任务中不可行。在本工作中,我们针对一般深度量子电路中的梯度消失问题,提出了一种具有理论保证的初始化策略。具体而言,我们证明了在适当的高斯初始化参数下,当量子比特数和电路深度增加时,梯度的范数至多以多项式速度衰减。我们的理论结果对局部可观测量和全局可观测量情形均成立,而后者曾被认为即使在非常浅的电路中也会出现梯度消失。实验结果在量子模拟和量子化学中验证了我们的理论发现。

英文摘要:

Variational quantum circuits have been widely employed in quantum simulation and quantum machine learning in recent years. However, quantum circuits with random structures have poor trainability due to the exponentially vanishing gradient with respect to the circuit depth and the qubit number. This result leads to a general standpoint that deep quantum circuits would not be feasible for practical tasks. In this work, we propose an initialization strategy with theoretical guarantees for the vanishing gradient problem in general deep quantum circuits. Specifically, we prove that under proper Gaussian initialized parameters, the norm of the gradient decays at most polynomially when the qubit number and the circuit depth increase. Our theoretical results hold for both the local and the global observable cases, where the latter was believed to have vanishing gradients even for very shallow circuits. Experimental results verify our theoretical findings in the quantum simulation and quantum chemistry.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑