Corpus ID: 54004501

Generalization Bounds for Uniformly Stable Algorithms

@inproceedings{Feldman2018GeneralizationBF,
  title={Generalization Bounds for Uniformly Stable Algorithms},
  author={V. Feldman and J. Vondr{\'a}k},
  booktitle={NeurIPS},
  year={2018}
}

V. Feldman, J. Vondrák

Published in NeurIPS 2018

Computer Science, Mathematics

Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002. [...] Key Result Our proofs are based on new analysis techniques and our results imply substantially stronger generalization guarantees for several well-studied algorithms.Expand Abstract

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed