Learnability and the Vapnik-Chervonenkis dimension
Citations
10 citations
10 citations
10 citations
10 citations
10 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...Learnability has always been one of the most central issues in machine learning, whereas the traditional work [Blumer et al., 1989; Alon et al., 1997; Shalev-Shwartz et al., 2010] can not be applied directly to ranking problems since the ranking loss is based on pairwise instances from different…...
[...]
...Learnability has always been one of the most central issues in machine learning, whereas the traditional work [Blumer et al., 1989; Alon et al., 1997; Shalev-Shwartz et al., 2010] can not be applied directly to ranking problems since the ranking loss is based on pairwise instances from different classes rather than single instance....
[...]
...A possible solution could be motivated from [Blumer et al., 1989] by considering the bipartite rank-shatter coefficient or introducing some new combinatorial parameters....
[...]
...The fundamental work [Blumer et al., 1989; Alon et al., 1997], at least for supervised classification and regression, showed that learnability is equivalent to the uniform convergence of the empirical risk to the expected risk, and that if a problem is learnable, it is learnable with ERM (Empirical…...
[...]
...The fundamental work [Blumer et al., 1989; Alon et al., 1997], at least for supervised classification and regression, showed that learnability is equivalent to the uniform convergence of the empirical risk to the expected risk, and that if a problem is learnable, it is learnable with ERM (Empirical Risk Minimizer)....
[...]
References
42,654 citations
40,020 citations
17,939 citations
14,948 citations
13,647 citations