噪声对量子神经网络过参数化的影响
Effects of noise on the overparametrization of quantum neural networks
AI总结:
本研究探讨噪声如何影响量子神经网络的过参数化,发现噪声可激活QFIM零特征值使网络欠参数化,但大噪声又指数抑制特征值,表明现有容量度量在硬件噪声下失效。
摘要:
过参数化是机器学习中最令人惊讶且臭名昭著的现象之一。近年来,已有若干研究探讨在无硬件噪声环境下运行的量子神经网络(QNN)是否以及如何被过参数化。特别地,有研究提出,若QNN拥有足够的参数以探索状态空间中的所有可用方向,则可将其定义为过参数化,即QNN输出态的量子Fisher信息矩阵(QFIM)的秩达到饱和。在此,我们探讨噪声的存在如何影响过参数化现象。我们的结果表明,噪声可以“激活”QFIM中先前为零的特征值,使得参数化状态能够探索原本不可及的方向,从而可能将过参数化的QNN转变为欠参数化的QNN。对于小噪声水平,QNN呈现准过参数化状态,因为大特征值与小特征值共存。随后,我们证明随着噪声幅度的增加,QFIM的所有特征值呈指数级抑制,表明状态对参数的任何变化变得不敏感。因此,存在一种拉锯效应:噪声既能开启新方向,也会抑制对参数更新的敏感性。最后,我们的结果暗示,当存在硬件噪声时,当前的QNN容量度量是定义不当的。
英文摘要:
Overparametrization is one of the most surprising and notorious phenomena in machine learning. Recently, there have been several efforts to study if, and how, Quantum Neural Networks (QNNs) acting in the absence of hardware noise can be overparametrized. In particular, it has been proposed that a QNN can be defined as overparametrized if it has enough parameters to explore all available directions in state space. That is, if the rank of the Quantum Fisher Information Matrix (QFIM) for the QNN's output state is saturated. Here, we explore how the presence of noise affects the overparametrization phenomenon. Our results show that noise can "turn on" previously-zero eigenvalues of the QFIM. This enables the parametrized state to explore directions that were otherwise inaccessible, thus potentially turning an overparametrized QNN into an underparametrized one. For small noise levels, the QNN is quasi-overparametrized, as large eigenvalues coexists with small ones. Then, we prove that as the magnitude of noise increases all the eigenvalues of the QFIM become exponentially suppressed, indicating that the state becomes insensitive to any change in the parameters. As such, there is a pull-and-tug effect where noise can enable new directions, but also suppress the sensitivity to parameter updates. Finally, our results imply that current QNN capacity measures are ill-defined when hardware noise is present.
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。