测量噪声对变分量子算法逃离鞍点的影响
Impact of Measurement Noise on Escaping Saddles in Variational Quantum Algorithms
AI总结:
本文研究VQE中测量散粒噪声如何帮助SGD逃离非凸损失景观的鞍点,发现逃离时间随噪声呈幂律下降并由$η/N_s$控制,且可用连续时间SDE解释。
摘要:
随机梯度下降(SGD)是经典机器学习和变分量子本征求解器(VQE)中常用的优化技术。对于在量子硬件上实现VQE,其结果总会受到测量散粒噪声的影响。然而,关于VQE中测量噪声的结构和性质,以及它如何促进优化,仍存在许多未知。在本工作中,我们分析测量噪声对优化动力学的影响。特别地,我们关注逃离损失景观中的鞍点,这在非凸损失函数的最小化中至关重要。我们发现,逃离时间(1)随测量噪声增加而以幂律方式减小,并且(2)可表示为$η/N_s$的函数,其中$η$是学习率,$N_s$是测量次数。后者意味着,当我们改变$η$和$N_s$但保持比值$η/N_s$固定时,逃离时间近似为常数。这种标度行为可以由离散时间SGD经连续时间近似得到的随机微分方程(SDE)很好地解释。根据该SDE,$η/N_s$被解释为测量散粒噪声的方差。这一结果告诉我们,可以通过基于连续时间SDE的分析来理解VQE中的优化动力学,而该理论在理论上比原始的离散时间SGD更简单。
英文摘要:
Stochastic gradient descent (SGD) is a frequently used optimization technique in classical machine learning and Variational Quantum Eigensolver (VQE). For the implementation of VQE on quantum hardware, the results are always affected by measurement shot noise. However, there are many unknowns about the structure and properties of the measurement noise in VQE and how it contributes to the optimization. In this work, we analyze the effect of measurement noise to the optimization dynamics. Especially, we focus on escaping from saddle points in the loss landscape, which is crucial in the minimization of the non-convex loss function. We find that the escape time (1) decreases as the measurement noise increases in a power-law fashion and (2) is expressed as a function of $η/N_s$ where $η$ is the learning rate and $N_s$ is the number of measurements. The latter means that the escape time is approximately constant when we vary $η$ and $N_s$ with the ratio $η/N_s$ held fixed. This scaling behavior is well explained by the stochastic differential equation (SDE) that is obtained by the continuous-time approximation of the discrete-time SGD. According to the SDE, $η/N_s$ is interpreted as the variance of measurement shot noise. This result tells us that we can learn about the optimization dynamics in VQE from the analysis based on the continuous-time SDE, which is theoretically simpler than the original discrete-time SGD.
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。