Convergence Analysis of coefficient-Based Regularization under moment Incremental condition
Convergence Analysis of coefficient-Based Regularization under moment Incremental condition
复制标题
DOI：
10.1142/s0219691314500088
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Cheng Wang;Jia Cai
中科院分区：
文献类型：
--
作者：
Cheng Wang;Jia Cai
本文研究了数据依赖假设空间中基于系数的正则化最小二乘回归问题。学习算法的实现与无限采样过程中绘制的样本和误差分析进行了垫脚石技术。提出了一种新的误差分解方法。我们设置中的正则化参数提供了更大的灵活性和自适应性。在矩假设条件下，通过l2-经验覆盖数解决了尖锐的学习率。
In this paper, we investigate coefficient-based regularized least squares regression problem in a data dependent hypothesis space. The learning algorithm is implemented with samples drawn by unbounded sampling processes and the error analysis is performed by a stepping-stone technique. A new error decomposition technique is proposed for the error analysis. The regularization parameters in our setting provide much more flexibility and adaptivity. Sharp learning rates are addressed by means of l2-empirical covering numbers under a moment hypothesis condition.