Multiclass boosting: margins, codewords, losses, and algorithms

MaRDI QIDQ5214229zbMATH OpenFDO

Authors Mohammad Saberian, Nuno Vasconcelos

Publication date 7 February 2020

Full work available at URL http://jmlr.csail.mit.edu/papers/v20/17-137.html

zbMATH Keywords

boostingloss functionmulticlass classificationmargin maximizationmulticlass boosting

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Multi-class \(\ell_2\)-Boost with the scoring coding
• Multi-class AdaBoost
• Multiclass boosting for weak classifiers
• A theory of multiclass boosting
• Multi-class boosting with asymmetric binary weak-learners

Cites work

• scientific article; zbMATH DE number 4070373 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1149409 (Why is no real title available?)
• scientific article; zbMATH DE number 3214054 (Why is no real title available?)
• scientific article; zbMATH DE number 3048077 (Why is no real title available?)
• 10.1162/15324430260185628
• A decision-theoretic generalization of on-line learning and an application to boosting
• A theory of multiclass boosting
• A view of margin losses as regularizers of probability estimates
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• Boosting. Foundations and algorithms.
• Classification by pairwise coupling
• Composite binary losses
• Improved boosting algorithms using confidence-rated predictions
• Locality-sensitive hashing scheme based on p-stable distributions
• Matrix Analysis
• Multi-class AdaBoost
• Multiclass boosting for weak classifiers
• Numerical Optimization
• On the learnability and design of output codes for multiclass problems
• Pattern classification.
• Reducing multiclass to binary: A unifying approach for margin classifiers
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• VC theory of large margin multi-category classifiers

Cited in

(7)

• Multi-class \(\ell_2\)-Boost with the scoring coding
• SVM-boosting based on Markov resampling: theory and algorithm
• New multicategory boosting algorithms based on multicategory Fisher-consistent losses
• Multi-class boosting with asymmetric binary weak-learners
• Multi-class learning by smoothed boosting
• A theory of multiclass boosting
• An improved multiclass LogitBoost using adaptive-one-vs-one

Describes a project that uses

Uses Software

• Caffe

This page was built for publication: Multiclass boosting: margins, codewords, losses, and algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5214229)