Title :
Endpoint learning for multilinear commutator of singular integral on space of homogeneous type
Author :
Shi, Jian-guo ; Wang, Juan ; Zhou, Meng ; Yin, Bing ; Shi, Yan-fang
Author_Institution :
Hebei Software Inst., Baoding, China
Abstract :
In this paper, we prove the endpoint estimates for the multilinear commutator related to the singular integral on the space of homogeneous type by means of the Lp (l <; p <; ∞) boundedness for the singular integral operator. The main tools of the proof are decomposition of function spaces and some general inequalities. The estimates we established are widely applied in support vector machines, especially the Minkowski´s inequality and Holde´s inequality which may have application to classification problems based on Kernel methods.
Keywords :
learning (artificial intelligence); pattern classification; support vector machines; Holde inequality; Minkowski inequality; classification problems; endpoint learning; function space decomposition; kernel methods; multilinear commutator; singular integral operator; support vector machines; Abstracts; BMO; Multilinear commutator; Singular integral; Space of homogeneous type;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2012 International Conference on
Conference_Location :
Xian
Print_ISBN :
978-1-4673-1484-8
DOI :
10.1109/ICMLC.2012.6359556