首页|Convergence analysis for complementary-label learning with kernel ridge regression

Convergence analysis for complementary-label learning with kernel ridge regression

扫码查看
原文链接
  • 万方数据
  • 维普
Complementary-label learning(CLL)aims at finding a classifier via samples with complementary labels.Such data is considered to contain less information than ordinary-label samples.The transition matrix between the true label and the complementary label,and some loss functions have been developed to handle this problem.In this paper,we show that CLL can be transformed into ordinary classification under some mild conditions,which indicates that the complementary labels can supply enough information in most cases.As an example,an extensive misclassification error analysis was performed for the Kernel Ridge Regression(KRR)method applied to multiple complementary-label learning(MCLL),which demonstrates its superior performance compared to existing approaches.

multiple complementary-label learningpartial label learningerror analysisreproducing kernel Hilbert spaces

NIE Wei-lin、WANG Cheng、XIE Zhong-hua

展开 >

School of Mathematics and Statistics,Huizhou University,Huizhou 516007,China

School of Computer Science and Engineering,Huizhou University,Huizhou 516007,China

Indigenous Innovation's Capability Development Program of Huizhou UniversityIndigenous Innovation's Capability Development Program of Huizhou UniversityNatural Science Foundation of Guangdong ProvinceProject of Educational Commission of Guangdong ProvinceNational Natural Science Foundation of ChinaGuangdong Province's 2023 Education Science Planning Project(Higher Education Special Project)

HZU202003HZU2020202022A15150114632023ZDZX1025122714732023GXJK505

2024

10.1007/s11766-024-5173-6

高校应用数学学报B辑(英文版)
浙江大学 中国工业与应用数学学会

高校应用数学学报B辑(英文版)

影响因子：0.146
ISSN：1005-1031
年,卷(期)：2024.39(3)