arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.01073stat.MLcs.LGmath.STstat.TH
收藏

再生核Krein空间中正则化最小二乘的分析

Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces

KU Leuven(鲁汶大学);Fudan University(复旦大学);Shanghai Jiao Tong University(上海交通大学)

Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

摘要:

本文研究再生核Krein空间(RKKS)中具有不定核的正则化最小二乘的渐近性质。通过引入一个有界超球面约束,证明了该问题存在一个全局最优解,且在球面上具有一个封闭形式,从而使得在RKKS中进行近似分析成为可能.对于由不定内积引入的正则化子,我们改进了传统的误差分解技术,基于矩阵扰动理论证明了引入假设误差的收敛性,并推导了RKKS中这类正则化回归问题的学习率.在一定条件下,RKKS中导出的学习率与再生核Hilbert空间(RKHS)中的学习率相同,这实际上是RKKS中正则化学习算法近似分析的第一个工作.

英文摘要:

In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS). By introducing a bounded hyper-sphere constraint to such non-convex regularized risk minimization problem, we theoretically demonstrate that this problem has a globally optimal solution with a closed form on the sphere, which makes approximation analysis feasible in RKKS. Regarding to the original regularizer induced by the indefinite inner product, we modify traditional error decomposition techniques, prove convergence results for the introduced hypothesis error based on matrix perturbation theory, and derive learning rates of such regularized regression problem in RKKS. Under some conditions, the derived learning rates in RKKS are the same as that in reproducing kernel Hilbert spaces (RKHS), which is actually the first work on approximation analysis of regularized learning algorithms in RKKS.

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。

↑