A more robust boosting algorithm
arXiv:0905.2138
Abstract
We present a new boosting algorithm, motivated by the large margins theory for boosting. We give experimental evidence that the new algorithm is significantly more robust against label noise than existing boosting algorithm.
Cited by in corpus (14)
- A Survey of Label-noise Representation Learning: Past, Present and Future
- Training a Large Scale Classifier with the Quantum Adiabatic Algorithm
- Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
- Boosting in the presence of outliers: adaptive classification with non-convex loss functions
- Robust Classification with Adiabatic Quantum Optimization
- Boosting in the presence of label noise
- Two-temperature logistic regression based on the Tsallis divergence
- Non-Convex Boosting Overcomes Random Label Noise
- A Semi-Supervised Method for Predicting Cancer Survival Using Incomplete Clinical Data
- Homotopy Continuation Approaches for Robust SV Classification and Regression
- CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise
- Vote-boosting ensembles
- Robust Semi-Supervised Graph Classifier Learning with Negative Edge Weights
- Robust Boosting for Regression Problems