论文标题
关于数据依赖性内核的内核回归
On Kernel Regression with Data-Dependent Kernels
论文作者
论文摘要
内核回归（KR）中的主要超参数是核的选择。在KR的大多数理论研究中，人们假设在查看训练数据之前固定了内核。在此假设下，众所周知，最佳内核等于目标函数的先前协方差。在本说明中，我们考虑在查看培训数据后可以更新内核的KR。我们指出，在这种情况下，使用目标函数后部的内核选择相似。讨论了与数据依赖性内核学习者的联系的联系。
The primary hyperparameter in kernel regression (KR) is the choice of kernel. In most theoretical studies of KR, one assumes the kernel is fixed before seeing the training data. Under this assumption, it is known that the optimal kernel is equal to the prior covariance of the target function. In this note, we consider KR in which the kernel may be updated after seeing the training data. We point out that an analogous choice of kernel using the posterior of the target function is optimal in this setting. Connections to the view of deep neural networks as data-dependent kernel learners are discussed.
