Algorithmic Stability and Meta-Learning

Abstract

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.

Cite

Text

Maurer. "Algorithmic Stability and Meta-Learning." Journal of Machine Learning Research, 2005.

Markdown

[Maurer. "Algorithmic Stability and Meta-Learning." Journal of Machine Learning Research, 2005.](https://mlanthology.org/jmlr/2005/maurer2005jmlr-algorithmic/)

BibTeX

@article{maurer2005jmlr-algorithmic,
  title     = {{Algorithmic Stability and Meta-Learning}},
  author    = {Maurer, Andreas},
  journal   = {Journal of Machine Learning Research},
  year      = {2005},
  pages     = {967-994},
  volume    = {6},
  url       = {https://mlanthology.org/jmlr/2005/maurer2005jmlr-algorithmic/}
}