当前位置:
X-MOL 学术
›
J. Complex.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
The recovery of ridge functions on the hypercube suffers from the curse of dimensionality
Journal of Complexity ( IF 1.8 ) Pub Date : 2020-10-14 , DOI: 10.1016/j.jco.2020.101521 Benjamin Doerr , Sebastian Mayer
中文翻译:
超立方体上的岭函数的恢复遭受维数的诅咒
更新日期:2020-10-14
Journal of Complexity ( IF 1.8 ) Pub Date : 2020-10-14 , DOI: 10.1016/j.jco.2020.101521 Benjamin Doerr , Sebastian Mayer
A multivariate ridge function is a function of the form , where is univariate and . We show that the recovery of an unknown ridge function defined on the hypercube with Lipschitz-regular profile suffers from the curse of dimensionality when the recovery error is measured in the -norm, even if we allow randomized algorithms. If a limited number of components of is substantially larger than the others, then the curse of dimensionality is not present and the problem is weakly tractable, provided the profile is sufficiently regular.
中文翻译:
超立方体上的岭函数的恢复遭受维数的诅咒
多元岭函数是形式的函数 ,在哪里 是单变量的 。我们显示了在超立方体上定义的未知岭函数的恢复 具有Lipschitz规则轮廓 当测量恢复误差时,会遭受尺寸的诅咒。 -范数,即使我们允许使用随机算法。如果部件数量有限 基本上大于其他维度,则不存在维数的诅咒,并且该问题很难解决。 有足够的规律性。