Corpus ID: 202766083

Margin-Based Generalization Lower Bounds for Boosted Classifiers

@inproceedings{Jrgensen2019MarginBasedGL,
  title={Margin-Based Generalization Lower Bounds for Boosted Classifiers},
  author={Allan Gr{\o}nlund J{\o}rgensen and Lior Kamma and Kasper Green Larsen and Alexander Mathiasen and Jelani Nelson},
  booktitle={NeurIPS},
  year={2019}
}
  • Allan Grønlund Jørgensen, Lior Kamma, +2 authors Jelani Nelson
  • Published in NeurIPS 2019
  • Mathematics, Computer Science
  • Boosting is one of the most successful ideas in machine learning. The most well-accepted explanations for the low generalization error of boosting algorithms such as AdaBoost stem from margin theory. The study of margins in the context of boosting algorithms was initiated by Schapire, Freund, Bartlett and Lee (1998), and has inspired numerous boosting algorithms and generalization bounds. To date, the strongest known generalization (upper bound) is the $k$th margin bound of Gao and Zhou (2013… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv