学术报告-林荣荣

发布人:
责任人:
点击数:
更新时间:
2018-10-12 10:37:00

学术报告

题      目:Multi-task Learning in Vector-valued Reproducing Kernel Banach Spaces with the l1 Norm


报  告  人:林荣荣     (邀请人: 叶颀)

                                 中山大学


时      间:2018-10-12 09:00--10:00

地      点:学院401

报告人简介:

      林荣荣博士于2017年6月在中山大学数学学院取得博士学位。博士期间作为科研助理曾访问加拿大阿尔伯特大学一年。2017年7月聘为中山大学数据科学与计算机学院副研究员。已在机器学习核函数方法和时频分析研究领域发表多篇论文。



摘      要:

       Motivated by sparse multi-task learning, we constructed a class of vector-valued reproducing kernel Banach spaces with the l1 norm based on multi-task admissible kernels. The linear representer theorem holds for regularization networks in the obtained spaces if and only if the Lebesgue constant of multi-task admissible kernels is bounded by 1. Examples including the Brownian bridge kernel, the exponential kernel and the covariance of Brownian motion admissible for constructions are given. In order to accommodate more kernels, we consider relaxed representer theorems that need a weaker condition on the Lebesgue constant. Finally, we present numerical experiments for both synthetic data and real-world benchmark data to demonstrate the advantages of the proposed construction and regularization models. This is a joint work with Prof.Guohui Song (Clarkson U) and Haizhang Zhang (SYSU).