AI 中文总结
该研究针对Hölder-Zygmund类的非参数回归,证明了设定错误的核岭回归可达到极小极大L2速率,同时发现其在Hölder-Zygmund范数下的正则化恰当性会随样本量增大失效。
AI 中文摘要
我们针对Hölder-Zygmund类上的非参数回归研究核岭回归(KRR)。利用与光滑度为s+d/2的Sobolev空间等价的RKHS,我们证明了模型设定错误的KRR可达到极小极大L2速率n^{-2s/(2s+d)}。我们还表明,在Hölder-Zygmund范数下正则化恰当性失效:即使回归函数为零且含高斯噪声,KRR噪声分量的期望平方Hölder-Zygmund范数仍随log n增长。
英文摘要
We study kernel ridge regression for nonparametric regression over the Hölder-Zygmund class. Using an RKHS equivalent to a Sobolev space of smoothness s+d/2, we prove that misspecified KRR attains the minimax L2 rate n^{-2s/(2s+d)}. We also show that properness fails in the Hölder-Zygmund norm: even for the zero regression function with Gaussian noise, the expected squared Hölder-Zygmund norm of the KRR noise component grows as log n.