报告名称:

Kernel-based Sparse Regression with the Correntropy-induced Loss

报告作者：

陈洪

作者简介：

所在学校：

华中农业大学

职称：

副教授

其他

博士

报告时间：

2015年10月26日(周一)下午2:30-4:00

报告地点：

英国威廉希尔体育公司201学术报告厅

报告摘要：

The correntropy-induced loss (C-loss) has been employed in learning algorithms

to improve their robustness to non-Gaussian noise and outliers recently. Despite its success on robust learning, only little work has been done to study the generalization performance of regularized regression with the C-loss. To enrich this theme, this paper investigates a kernel-based regression algorithm with the C-loss and l_1 regularizer in data dependent hypothesis spaces. The asymptotic learning rate is established for the proposed algorithm in terms of novel error decomposition and capacity-based analysis technique. The sparsity characterization of the derived predictor is studied theoretically. Empirical evaluations demonstrate its advantages over the related approaches. Finally, some extensions are also discussed.