19 July 2013 Strong and weak stability of bipartite ranking algorithms
Author Affiliations +
Proceedings Volume 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013); 88783W (2013) https://doi.org/10.1117/12.2030493
Event: Fifth International Conference on Digital Image Processing, 2013, Beijing, China
Abstract
Ranking is an important problem in information retrieval and other applications, a good ranking algorithm should have good stability, which means for a wild change of samples, the ranking function doesn’t change too much. Among the existent ranking algorithms, the bipartite ranking is a special kind of ranking method, the goal of bipartite ranking is to learn a score function from positive and negative training samples that induces a ranking for an instance space. In this paper, the ‘almost everywhere’ stability of bipartite ranking algorithms is investigated, notions of strong stability and weak stability for bipartite ranking algorithms are defined, and the generalization bounds of stable bipartite ranking algorithms are obtained. In particular, the relationship between strong (weak) loss stability and strong (weak) score stability is also discussed.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Gao, Yungang Zhang, Yun Gao, Li Liang, Youming Xia, "Strong and weak stability of bipartite ranking algorithms", Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 88783W (19 July 2013); doi: 10.1117/12.2030493; https://doi.org/10.1117/12.2030493
PROCEEDINGS
7 PAGES


SHARE
Back to Top