arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.03757cs.LGcs.DCstat.ML
收藏

相依样本分布式学习

Distributed Learning with Dependent Samples

Zirui Sun, Shao-Bo Lin

摘要:

研究强混合序列下分布核岭回归的学习率分析。利用最近发展起来的积分算子方法和Banach值强混合序列的经典协方差不等式,我们成功地导出了分布核岭回归的最优学习率.作为一个副产品,我们还推出了一个充分条件的混合性质,以保证最佳的学习率的核岭回归。我们的结果扩展了i.i.d.分布式学习的适用范围样本至非i.i.d.序列的

英文摘要:

This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridge regression. As a byproduct, we also deduce a sufficient condition for the mixing property to guarantee the optimal learning rates for kernel ridge regression. Our results extend the applicable range of distributed learning from i.i.d. samples to non-i.i.d. sequences.

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。

↑