arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02055math.NAcs.NA
收藏

限制于iid采样的Sobolev函数的恢复

Recovery of Sobolev functions restricted to iid sampling

David Krieg, Erich Novak, Mathias Sonnleitner

摘要:

我们研究$L_q$ -近似和集成功能从索伯列夫空间$W^s_p(Ω)$和比较最佳随机(蒙特卡罗)算法,只能使用iid样本点,均匀分布在域上的算法。主要的结果是,我们获得相同的最佳收敛速率,如果我们限制到iid采样,在学习和不确定性量化的共同假设。唯一的例外是当使用$p=q=\infty$时,无法避免对数损失。

英文摘要:

We study $L_q$-approximation and integration for functions from the Sobolev space $W^s_p(Ω)$ and compare optimal randomized (Monte Carlo) algorithms with algorithms that can only use iid sample points, uniformly distributed on the domain. The main result is that we obtain the same optimal rate of convergence if we restrict to iid sampling, a common assumption in learning and uncertainty quantification. The only exception is when $p=q=\infty$, where a logarithmic loss cannot be avoided.

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。

↑