Stability Analysis for Local Transductive Regression Algorithms
In this paper, the stability of local transductive regression algorithms is studied by adopting a strategy which adjusts the sample set by removing one or two elements from it. A sufficient condition for uniform stability is given. The result of our work shows that if a local transductive regression algorithm uses square loss, and if for any x, a kernel function K(x, x) has a limited upper bound, then the local transductive regression algorithm which minimizes the standard form will have good uniform stability.
W. Gao et al., "Stability Analysis for Local Transductive Regression Algorithms", Advanced Materials Research, Vol. 267, pp. 438-443, 2011