Distributed learning with indefinite kernels

Distributed learning with indefinite kernels
复制标题

具有不定内核的分布式学习

DOI:
10.1142/s021953051850032x
复制
发表时间:
2019-09
影响因子:
2.2
通讯作者:
L. Shi
L. Shi
中科院分区:
数学3区
文献类型:
--
作者:
L. Shi

文献摘要

参考文献

相似文献

在核回归方法的框架下,研究了基于系数正则化的分布式学习问题。与经典的核岭回归(KRR)算法相比,该算法不要求核函数为半正定,从而为设计不定核方法提供了一种简单的范例。分布式学习方法将海量数据集分成几个不相交的数据子集,然后通过取每个数据子集上的局部估计器的平均值来产生全局估计器。与在整个样本上执行原始算法的标准方法相比,易于执行的划分和在每个子集上并行执行算法导致了计算时间的显著减少。我们建立了具有不定核的分布式系数正则化格式的第一个最小-最大最优收敛速度。因此,与分布式KRR算法相比,该算法在处理大规模数据集的回归问题上更加灵活和有效。
We investigate the distributed learning with coefficient-based regularization scheme under the framework of kernel regression methods. Compared with the classical kernel ridge regression (KRR), the algorithm under consideration does not require the kernel function to be positive semi-definite and hence provides a simple paradigm for designing indefinite kernel methods. The distributed learning approach partitions a massive data set into several disjoint data subsets, and then produces a global estimator by taking an average of the local estimator on each data subset. Easy exercisable partitions and performing algorithm on each subset in parallel lead to a substantial reduction in computation time versus the standard approach of performing the original algorithm on the entire samples. We establish the first mini-max optimal rates of convergence for distributed coefficient-based regularization scheme with indefinite kernels. We thus demonstrate that compared with distributed KRR, the concerned algorithm is more flexible and effective in regression problem for large-scale data sets.
使用 l1 范数再现内核 Banach 空间
DOI: 10.1016/j.acha.2012.03.009
发表时间: 2011-01
影响因子: 2.5
作者:
Guohui Song;Haizhang Zhang;Fred J. Hickernell
通讯作者: Fred J. Hickernell
具有不定核的正则化网络
DOI: 10.1016/j.jat.2012.10.001
发表时间: 2013-02
影响因子: 0.9
作者:
Qiang Wu
通讯作者: Qiang Wu
DOI: 10.1090/s0002-9947-1950-0051437-7
发表时间: 1950-01-01
影响因子: 1.3
作者:
ARONSZAJN, N
通讯作者: ARONSZAJN, N
DOI: 10.1162/neco_a_00641
发表时间: 2013-12
期刊: Neural Computation
影响因子: 2.9
作者:
Shaobo Lin;Jinshan Zeng;Jian Fang;Zongben Xu
通讯作者: Shaobo Lin;Jinshan Zeng;Jian Fang;Zongben Xu
DOI: --
发表时间: 2005-12
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
Cheng Soon Ong;Alex Smola;R. C. Williamson
通讯作者: Cheng Soon Ong;Alex Smola;R. C. Williamson