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.