AdaBoost is consistent

MaRDI QIDQ3174158zbMATH OpenFDO

Authors Peter L. Bartlett, Mikhail Traskin

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v8/bartlett07b.html

zbMATH Keywords

boostingconsistencyAdaBoost

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 2089370
• Process consistency for AdaBoost.
• On the Bayes-risk consistency of regularized boosting methods.
• The rate of convergence of AdaBoost
• Boosting with early stopping: convergence and consistency

Cited in

(23)

• Boosting simple learners
• Collective-agreement-based pruning of ensembles
• A new accelerated proximal boosting machine with convergence rate \(O(1/t^2)\)
• Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
• SVM-boosting based on Markov resampling: theory and algorithm
• A simple extension of boosting for asymmetric mislabeled data
• Calibrating AdaBoost for phoneme classification
• Fast iterative regularization by reusing data
• Accelerated gradient boosting
• Utilizing adaptive boosting to detect quantum steerability
• The vanishing learning rate asymptotic for linear \(L^2\)-boosting
• Consistency and convergence rate for nearest subspace classifier
• Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping
• A boosting method with asymmetric mislabeling probabilities which depend on covariates
• A new integrated discrimination improvement index via odds
• Process consistency for AdaBoost.
• Boosting k-NN for categorization of natural scenes
• Deformation of log-likelihood loss function for multiclass boosting
• Boosting algorithms: regularization, prediction and model fitting
• Random classification noise defeats all convex potential boosters
• Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications
• Optimization by Gradient Boosting
• A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers

This page was built for publication: AdaBoost is consistent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174158)