Algorithmic Stability and Meta-Learning

A mechnism of transfer learning is analysed, where samples drawn from different learning tasks of an environment are used to improve the learners performance on a new task. We give a general method to prove generalisation error bounds for such meta-algorithms. The method can be applied to the bias learning model of J. Baxter and to derive novel generalisation bounds for meta-algorithms searching spaces of uniformly stable algorithms. We also present an application to regularized least squares regression. [abs] [ pdf ][ bib ] © JMLR 2005. (edit, beta)