Stability of Transductive Regression Algorithms
Corinna Cortes, Mehryar Mohri, Dmitry Pechyony and Ashish Rastogi
In: ICML 2008, 5-9 July, 2008, Helsinki, Finland.
This paper uses the notion of algorithmic stability
to derive novel generalization bounds
for several families of transductive regression
algorithms, both by using convexity and
closed-form solutions. Our analysis helps
compare the stability of these algorithms.
It suggests that several existing algorithms
might not be stable but prescribes a technique
to make them stable. It also reports
the results of experiments with local transductive
regression demonstrating the benefit
of our stability bounds for model selection, in
particular for determining the radius of the
local neighborhood used by the algorithm.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Theory & Algorithms|
|Deposited By:||Dmitry Pechyony|
|Deposited On:||24 March 2009|