Arcing classifier (with discussion and a rejoinder by the author)
By Leo Breiman. 1998
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Francis R. Bach
- Dacheng Tao
- Sergey Levine
- Luc Van Gool
- Cynthia Rudin
- Percy Liang
- Quoc V. Le
Citations in the corpus
- Model Zoo: A Growing Brain That Learns Continually (2021, methodology): “Recall the AdaBoost algorithm which builds an ensemble of weak learners (they can be any learner in principle Mason et al. (1999)), each of which is fitted upon iteratively re-weighted training data (Breiman, 1998).”
- Ensemble Classification and Regression-Recent Developments, Applications and Future Directions [Review Article] (2016, methodology): “There are several AdaBoost variants for classification such as: confidence-rated AdaBoost for multi-class classification [51]; soft margin AdaBoost with regularization [52]; Modest AdaBoost [53] and its improved modification with a weighting system [54]; SpatialBoost [55] that incorporates spatial r”
- Bandwidth choice for nonparametric classification (2005, background): “It is less closely connected to classification problems involving very high-dimensional data; for the latter setting, see, for example, Breiman (1998, 2001), Schapire, Freund, Bartlett and Lee (1998), Friedman, Hastie and Tibshirani (2000), Kim and Loh (2001), Dudoit, Fridlyand and Speed (2002) and…”
- A survey of cross-validation procedures for model selection (2009, unknown): “CV was raised to fix this issue (Mosteller and Tukey, 1968; Stone, 1974; Geisser, 1975), starting from the remark that testing the output of the algorithm on new data would yield a good estimate of its performance (Breiman, 1998).”
- To combine or not to combine: selecting among forecasts and their combinations (2005, methodology): “…in the variance of the performance across the combinations relative to the variance across the individual methods, for various measures of variance (Breiman, 1998; Evgeniou, Pontil & Elisseeff, 2004); b) the variance across a number of methods is related to the risk (as defined in hypothesis H4)…”