Minimax-optimal classification with dyadic decision trees

DOI10.1109/TIT.2006.871056MaRDI QIDQ3547602zbMATH OpenFDO

Authors Clayton Scott, Robert D. Nowak

Publication date 21 December 2008

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TIT.2006.871056

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Pattern recognition, speech recognition (68T10) Detection theory in information and communication theory (94A13)

Recommendations

• Optimal dyadic decision trees
• Learning Theory
• Algorithms for optimal dyadic decision trees
• Optimal classification trees
• Feature minimization within decision trees

Cited in

(33)

• Classification with minimax fast rates for classes of Bayes rules with sparse representation
• Penalized empirical risk minimization over Besov spaces
• Algorithms for optimal dyadic decision trees
• Adaptive estimation of multivariate piecewise polynomials and bounded variation functions by optimal decision trees
• Adaptive learning rates for support vector machines working on data with low intrinsic dimension
• Uncertainty quantification for Bayesian CART
• Adaptive transfer learning
• Optimal survival trees
• Learning Bayesian networks with local structure, mixed variables, and exact algorithms
• Minimax-optimal nonparametric regression in high dimensions
• Optimal dyadic decision trees
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• Risk bounds for CART classifiers under a margin condition
• A tree-based regressor that adapts to intrinsic dimension
• Making decision trees feasible in ultrahigh feature and label dimensions
• Learning Theory
• Online Adaptive Decision Trees
• Classification algorithms using adaptive partitioning
• Intrinsic dimension adaptive partitioning for kernel methods
• Polynomial mixing of the edge-flip Markov chain for unbiased dyadic tilings
• Classification Trees for Imbalanced Data: Surface-to-Volume Regularization
• A cross-validation framework for signal denoising with applications to trend filtering, dyadic CART and beyond
• Quantile regression by dyadic CART
• Regularized impurity reduction: accurate decision trees with complexity guarantees
• Time-penalised trees (\texttt{TpT}): introducing a new tree-based data mining algorithm for time-varying covariates
• Hyper-pyramid-adapted shearlet transform with application to compressive level set estimation
• Robust discrete Bayesian classifier under covariate and label noise
• A finite-horizon approach to active level set estimation
• Self-tuning bandits over unknown covariate-shifts
• Adaptive Bayesian regression on data with low intrinsic dimensionality
• On signal representations within the Bayes decision framework
• On the minimization of concave information functionals for unsupervised classification via decision trees
• Complexity-penalized estimation of minimum volume sets for dependent data

This page was built for publication: Minimax-optimal classification with dyadic decision trees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3547602)