论文标题
关于基于内核的成对学习的鲁棒性
On the robustness of kernel-based pairwise learning
论文作者
论文摘要
结果表明，基于内核成对学习的统计鲁棒性的许多结果可以在基本上没有在输入和输出空间上的假设下得出。特别是，在给定x = x的条件分布上，不需要输出空间的界限。我们获得了影响函数的存在和界限的结果，并显示了基于内核的估计器的定性鲁棒性。本文通过允许预测函数进行两个论点，因此可以在各种情况下（例如排名）中应用，从而概括了Christmann and Zhou（2016）的结果。
It is shown that many results on the statistical robustness of kernel-based pairwise learning can be derived under basically no assumptions on the input and output spaces. In particular neither moment conditions on the conditional distribution of Y given X = x nor the boundedness of the output space is needed. We obtain results on the existence and boundedness of the influence function and show qualitative robustness of the kernel-based estimator. The present paper generalizes results by Christmann and Zhou (2016) by allowing the prediction function to take two arguments and can thus be applied in a variety of situations such as ranking.
