Deep Boosting

By Corinna Cortes, Mehryar Mohri, Umar Syed. 2014

106 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

AdaNet: Adaptive Structural Learning of Artificial Neural Networks (2016, methodology): “Our algorithm can be viewed as an instance of the DeepBoost algorithm of Cortes et al. [2014].”
Learning Deep ResNet Blocks Sequentially using Boosting Theory (2017, background): “(Theorem 1 (Cortes et al., 2014)) Let H be a hypothesis set admitting a decomposition H = ∪i=1Hi for some l > 1.”
Ensemble deep learning: A review (2021, methodology): “[60] Decision trees as base classifiers for binary class classification problems.”
Ensemble learning: A survey (2018, background): “A recent work presented boosting limitations in achieving good performance in difficult classification tasks such as speech and image recognition (Cortes, Mohri, & Syed, 2014).”
IPBoost - Non-Convex Boosting via Integer Programming (2020, methodology): “For example, in (Cortes et al., 2014) boosting across classes of more complex learners has been considered and the αj are chosen to be proportional to the Rademacher complexity of the learners (many other measures might be equally justified).”
Multi-Class Deep Boosting (2014, background): “Our result generalizes the main result of Cortes et al. [2014] to the multi-class setting, and also represents an improvement on the multi-class generalization bound due to Koltchinskii and Panchenko [2002], even if we disregard our finer analysis related to Rademacher complexity. In Section 3, we p”
A comprehensive review on ensemble deep learning: Opportunities and challenges (2023, background): “In particular, in medical image classiﬁcation, the researchers in Cortes et al. (2014) suggested boosting based on deep decision tree (DT) for image classiﬁcation using several breast cancer datasets.”