Generalization error of minimum weighted norm and kernel interpolation

Generalization error of minimum weighted norm and kernel interpolation
复制标题

最小加权范数和核插值的泛化误差

DOI:
10.1137/20m1359912
复制
发表时间:
2020
期刊:
SIAM J. Math. Data Sci.
影响因子:
--
通讯作者:
Weilin Li
Weilin Li
中科院分区:
--
文献类型:
--
作者:
Weilin Li

文献摘要

参考文献

被引文献

相似文献

我们研究了插值指定数据点的函数的泛化误差,并通过最小化加权范数来选择。在自然条件和一般条件下,我们证明了插值量及其泛化误差随着参数数目的增加而收敛,并且证明了极限插值量属于可复制核Hilbert空间。这严格地建立了最小加权范数插值的隐式偏差,并解释了为什么范数最小化可能受益于过度参数化。作为该理论的特例,我们研究了三角多项式和球谐插值。我们的方法是从确定性和近似理论的观点出发,而不是从统计或随机矩阵的观点出发。
We study the generalization error of functions that interpolate prescribed data points and are selected by minimizing a weighted norm. Under natural and general conditions, we prove that both the interpolants and their generalization errors converge as the number of parameters grow, and the limiting interpolant belongs to a reproducing kernel Hilbert space. This rigorously establishes an implicit bias of minimum weighted norm interpolation and explains why norm minimization may benefit from over-parameterization. As special cases of this theory, we study interpolation by trigonometric polynomials and spherical harmonics. Our approach is from a deterministic and approximation theory viewpoint, as opposed a statistical or random matrix one.
DOI: --
发表时间: 2018-06
期刊: ArXiv
影响因子: --
作者:
M. Belkin;A. Rakhlin;A. Tsybakov
通讯作者: M. Belkin;A. Rakhlin;A. Tsybakov
DOI: 10.1002/cpa.22008
发表时间: 2019-08
影响因子: 3
作者:
Song Mei;A. Montanari
通讯作者: Song Mei;A. Montanari
DOI: 10.1073/pnas.1903070116
发表时间: 2019-08-06
影响因子: 11.1
作者:
Belkin, Mikhail;Hsu, Daniel;Mandal, Soumik
通讯作者: Mandal, Soumik