Vector-valued Reproducing Kernel Banach Spaces with Applications to Multi-task Learning

11/04/2011
by   Haizhang Zhang, et al.
0

Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RKBS. The theory is then applied to multi-task machine learning. Especially, the representer theorem and characterization equations for the minimizer of regularized learning schemes in vector-valued RKBS are established.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/17/2013

Stability of Multi-Task Kernel Regression Algorithms

We study the stability properties of nonlinear multi-task regression in ...
research
04/01/2021

Learning Rates for Multi-task Regularization Networks

Multi-task learning is an important trend of machine learning in facing ...
research
04/13/2015

Learning Multiple Visual Tasks while Discovering their Structure

Multi-task learning is a natural approach for computer vision applicatio...
research
06/05/2016

Bounds for Vector-Valued Function Estimation

We present a framework to derive risk bounds for vector-valued learning ...
research
08/20/2020

No-regret Algorithms for Multi-task Bayesian Optimization

We consider multi-objective optimization (MOO) of an unknown vector-valu...
research
01/04/2019

On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions

Recently, there has been emerging interest in constructing reproducing k...
research
02/09/2021

Emotion Transfer Using Vector-Valued Infinite Task Learning

Style transfer is a significant problem of machine learning with numerou...

Please sign up or login with your details

Forgot password? Click here to reset