量子神经网络损失景观的统一理论
A Unified Theory of Quantum Neural Network Loss Landscapes
AI总结：
本文提出统一理论，证明量子神经网络及其导数一般形成Wishart过程，并据此首次给出高斯过程极限条件、完整梯度分布和局部极小值分布，进而用“自由度”定义QNN可训练性。
摘要：
随机初始化的经典神经网络在神经元数量趋于无穷的极限下以高斯过程的形式表现，这一著名性质使人们能够完全刻画其训练和泛化行为。对于量子神经网络（QNNs），目前尚不存在这样的一般性理解——除某些特殊情况外，已知随机初始化的QNN并不表现为高斯过程。本文证明，QNN及其前两阶导数通常形成我们所称的“Wishart过程”，其中网络的某些代数性质决定了该过程的超参数。这一Wishart过程描述使我们首次能够：给出QNN架构具有高斯过程极限的充分必要条件；计算完整的梯度分布，推广了先前已知的贫瘠高原结果；并计算代数约束QNN的局部极小值分布。我们的统一框架通过引入一个新提出的、实验上可获取的量——网络架构的“自由度”，为给定QNN模型的“可训练性”提供了一个简单的操作性定义。
英文摘要：
Classical neural networks with random initialization famously behave as Gaussian processes in the limit of many neurons, which allows one to completely characterize their training and generalization behavior. No such general understanding exists for quantum neural networks (QNNs), which -- outside of certain special cases -- are known to not behave as Gaussian processes when randomly initialized. We here prove that QNNs and their first two derivatives instead generally form what we call "Wishart processes," where certain algebraic properties of the network determine the hyperparameters of the process. This Wishart process description allows us to, for the first time: give necessary and sufficient conditions for a QNN architecture to have a Gaussian process limit; calculate the full gradient distribution, generalizing previously known barren plateau results; and calculate the local minima distribution of algebraically constrained QNNs. Our unified framework suggests a certain simple operational definition for the "trainability" of a given QNN model using a newly introduced, experimentally accessible quantity we call the "degrees of freedom" of the network architecture.
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。
