Multi-Class Deep Boosting

82 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.

Cross-Entropy Loss Functions: Theoretical Analysis and Applications (2023, background): “Another line of research focuses on realizable H-consistency guarantees (Long & Servedio, 2013; Zhang & Agarwal, 2020; Kuznetsov et al., 2014), which provides hypothesis set-specific consistency guarantees under the assumption that the underlying distribution is H-realizable.”
Ensemble deep learning: A review (2021, background): “Multiclass Deep boosting [61] extended the Deep boosting [60] algorithm to theoretical, algorithmic, and empirical results to the multiclass problems.”
Structured Prediction Theory Based on Factor Graph Complexity (2016, methodology): “In that case, for linear hypotheses, the complexity term of our bound varies as O(Λ2r2 √ c/ρ2m) for example for norm-2 regularization (Corollary 10), which improves upon the best known general margin bounds of Kuznetsov et al. [2014], who provide a guarantee that scales linearly with the number of c”
A comprehensive review on ensemble deep learning: Opportunities and challenges (2023, methodology): “The researchers in Kuznetsov et al. (2014) used AdaBoost based on DT for multi-class classiﬁcation using 8 UCI datasets (Fernández-Delgado et al., 2014).”