Multi task Learning in Vector valued Reproducing Kernel Banach Spaces with the l1 Norm

Time: 2021-08-08 11:09:00

Topic：Multi task Learning in Vector valued Reproducing Kernel Banach Spaces with the l1 Norm

Speaker：Rongrong Lin      Guangdong University of Technology 

Time：2021-08-07 15:00--17:00

Location：Room 201

Introduction：

    Targeting at sparse multi-task learning, we consider regularization models with an l1 penalty on the coefficients of kernel functions. In order to provide a kernel method for this model, we construct a class of vector-valued reproducing kernel Banach spaces with the l1 norm. The notion of multi-task admissible kernels is proposed so that the constructed spaces could have desirable properties including the crucial linear representer theorem. Such kernels are related to bounded Lebesgue constants of a kernel interpolation question. We study the Lebesgue constant of multi-task kernels and provide examples of admissible kernels. This is a joint work with Prof. Guohui Song (ODU) and Haizhang Zhang (SYSU).