On the doubt about margin explanation of boosting

@article{Gao2013OnTD,
  title={On the doubt about margin explanation of boosting},
  author={W. Gao and Z. Zhou},
  journal={Artif. Intell.},
  year={2013},
  volume={203},
  pages={1-18}
}
  • W. Gao, Z. Zhou
  • Published 2013
  • Computer Science, Mathematics
  • Artif. Intell.
Margin theory provides one of the most popular explanations to the success of AdaBoost, where the central point lies in the recognition that margin is the key for characterizing the performance of AdaBoost. This theory has been very influential, e.g., it has been used to argue that AdaBoost usually does not overfit since it tends to enlarge the margin even after the training error reaches zero. Previously the minimum margin bound was established for AdaBoost, however, Breiman (1999) [9] pointed… Expand
Margins are Insufficient for Explaining Gradient Boosting
Margin-Based Generalization Lower Bounds for Boosted Classifiers
Large margin distribution machine
Optimal Margin Distribution Machine
  • Teng Zhang, Z. Zhou
  • Computer Science, Mathematics
  • IEEE Transactions on Knowledge and Data Engineering
  • 2020
Large Margin Distribution Learning
Generalization improvement for regularized least squares classification
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 74 REFERENCES
A Refined Margin Analysis for Boosting Algorithms via Equilibrium Margin
Boosting in the Limit: Maximizing the Margin of Learned Ensembles
How boosting the margin can also boost classifier complexity
Soft Margins for AdaBoost
Boosting Through Optimization of Margin Distributions
The Rate of Convergence of Adaboost
Data-dependent margin-based generalization bounds for classification
...
1
2
3
4
5
...