基于独立但不同分布样本的系数正则化回归算法的研究  

Analysis of Coefficient Regularized Regression with Non-Identically and Independently Sampling

作　　者：常欣欣 王鑫[1] 

机构地区：[1]安阳工学院,河南 安阳

出　　处：《应用数学进展》2021年第10期3254-3260,共7页Advances in Applied Mathematics

摘　　要：本文分析了基于独立但不同分布样本的系数正则化回归学习算法。全文的框架不同于以往的经典核学习方法,核函数不再要求满足半正定性;对于样本输出,令其满足弱化的矩假设条件。文章使用积分算子的方法得到了满意的与容量无关的误差界,最后通过选取合适的正则化参数得到较为满意的学习率。This paper considers the error analysis of coefficient regularization with non-identically and independently sampling. The framework under investigation is different from classical kernel learning. The kernel function no longer satisfies the positive semidefiniteness;we carry out the error analysis with output sample values satisfying a generalized moment hypothesis. Satisfactory capacity independently error bounds are derived by the techniques of integral operator for this learning algorithm, finally, a satisfactory learning rate is obtained by selecting appropriate regularization parameters.

关 键 词：系数正则化回归 非正定核 矩假设条件 积分算子 学习率 

分 类 号：O17[理学—数学]