Oracle Bounds and Exact Algorithm for Dyadic Classification Trees

This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multiclass classification problem. The estimator is based on model selection by penalized empirical loss minimization. Our work consists in two complementary parts: first, a theoretical analysis of the method leads to deriving oracle-type inequalities for three different possible loss functions. Secondly, we present an algorithm able to compute the estimator in an exact way. 1 General setup

• Type: Conference
• Year: 2004
• Where: COLT
• Authors: Gilles Blanchard, Christin Schäfer, Yves Rozenholc
• Keywords: COLT 2004, Dyadic Decision Trees, Machine Learning, Multiclass Classification Problem, Penalized Empirical Loss