Online minimum error entropy algorithm with unbounded sampling

Online minimum error entropy algorithm with unbounded sampling
复制标题

无界采样在线最小误差熵算法

DOI:
10.1142/s0219530518500148
复制
发表时间:
2019-03
影响因子:
2.2
通讯作者:
Ting Hu
Ting Hu
中科院分区:
数学3区
文献类型:
--
作者:
Cheng Wang;Ting Hu

文献摘要

参考文献

被引文献

相似文献

最小误差熵准则是信息论学习中一种重要的优化方法,在各种实际应用中得到了广泛的应用和研究。本文将介绍一种处理大数据集的在线递归算法,该算法与再生核希尔伯特空间(RKHS)和无界采样过程相结合。在回归函数正则性和多项式衰减步长的条件下,给出了显式收敛速度。除了它的低复杂度,我们还将表明,学习能力的在线学习是上级的文献中以前的工作。我们的主要技术依赖于RKHS上的积分算子和Hilbert空间中随机变量的概率不等式。
Minimum error entropy (MEE) criterion is an important optimization method in information theoretic learning (ITL) and has been widely used and studied in various practical scenarios. In this paper, we shall introduce the online MEE algorithm for dealing with big datasets, associated with reproducing kernel Hilbert spaces (RKHS) and unbounded sampling processes. Explicit convergence rate will be given under the conditions of regularity of the regression function and polynomially decaying step sizes. Besides its low complexity, we will also show that the learning ability of online MEE is superior to the previous work in the literature. Our main techniques depend on integral operators on RKHS and probability inequalities for random variables with values in a Hilbert space.
DOI: 10.1080/01621459.1962.10482149
发表时间: 1962-03
影响因子: 3.7
作者:
G. Bennett
通讯作者: G. Bennett
DOI: 10.1214/aop/1176988477
发表时间: 1994-10
影响因子: 2.3
作者:
I. Pinelis
通讯作者: I. Pinelis
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: 10.1016/j.acha.2014.12.005
发表时间: 2014-12
期刊: ArXiv
影响因子: --
作者:
Jun Fan;Ting Hu;Qiang Wu;Ding-Xuan Zhou
通讯作者: Jun Fan;Ting Hu;Qiang Wu;Ding-Xuan Zhou
DOI: 10.1214/aoms/1177704472
发表时间: 1962-01-01
影响因子: --
作者:
PARZEN, E
通讯作者: PARZEN, E