论文标题
尽管量子机学习模型过于拟合，但概括
Generalization despite overfitting in quantum machine learning models
论文作者
论文摘要
深度神经网络的广泛成功揭示了古典机器学习中的一个惊喜：非常复杂的模型通常可以很好地推广，同时又过度拟合培训数据。已经研究了各种古典模型的良性过度拟合现象，目的是更好地了解深度学习背后的机制。在量子机学习背景下表征现象可能会提高我们对过度拟合，过度参数化和概括之间关系的理解。在这项工作中，我们提供了量子模型中过度拟合的特征。为此，我们得出了在噪声信号上进行回归的经典插值傅立叶特征模型的行为，并展示了一类量子模型如何表现出类似的特征，从而将量子电路（例如数据编码和状态制备操作）的结构链接到量子模型中的量子电路（例如数据编码和状态制备操作）中。我们会根据量子模型以局部“尖峰”行为插值嘈杂数据的能力来凭直觉解释这些特征，并提供了良性过度拟合的具体演示示例。
The widespread success of deep neural networks has revealed a surprise in classical machine learning: very complex models often generalize well while simultaneously overfitting training data. This phenomenon of benign overfitting has been studied for a variety of classical models with the goal of better understanding the mechanisms behind deep learning. Characterizing the phenomenon in the context of quantum machine learning might similarly improve our understanding of the relationship between overfitting, overparameterization, and generalization. In this work, we provide a characterization of benign overfitting in quantum models. To do this, we derive the behavior of a classical interpolating Fourier features models for regression on noisy signals, and show how a class of quantum models exhibits analogous features, thereby linking the structure of quantum circuits (such as data-encoding and state preparation operations) to overparameterization and overfitting in quantum models. We intuitively explain these features according to the ability of the quantum model to interpolate noisy data with locally "spiky" behavior and provide a concrete demonstration example of benign overfitting.
