Fast Learning Rates for Plug-in Classifiers by Jean-yves Audibert
نویسنده
چکیده
It has been recently shown that, under the margin (or low noise) assumption, there exist classifiers attaining fast rates of convergence of the excess Bayes risk, that is, rates faster than n−1/2. The work on this subject has suggested the following two conjectures: (i) the best achievable fast rate is of the order n−1, and (ii) the plug-in classifiers generally converge more slowly than the classifiers based on empirical risk minimization. We show that both conjectures are not correct. In particular, we construct plug-in classifiers that can achieve not only fast, but also super-fast rates, that is, rates faster than n−1. We establish minimax lower bounds showing that the obtained rates cannot be improved.
منابع مشابه
Fast Learning Rates for Plug-in Classifiers
It has been recently shown that, under the margin (or low noise) assumption, there exist classifiers attaining fast rates of convergence of the excess Bayes risk, i.e., the rates faster than n−1/2. The works on this subject suggested the following two conjectures: (i) the best achievable fast rate is of the order n−1, and (ii) the plug-in classifiers generally converge slower than the classifie...
متن کاملFast learning rates for plug-in classifiers under the margin condition
It has been recently shown that, under the margin (or low noise) assumption, there exist classifiers attaining fast rates of convergence of the excess Bayes risk, i.e., the rates faster than n−1/2. The works on this subject suggested the following two conjectures: (i) the best achievable fast rate is of the order n−1, and (ii) the plug-in classifiers generally converge slower than the classifie...
متن کاملThéorie Statistique de l’Apprentissage: une approche PAC-Bayésienne PAC-Bayesian Statistical Learning Theory
This PhD thesis is a mathematical study of the learning task – specifically classification and least square regression – in order to better understand why an algorithm works and to propose more efficient procedures. The thesis consists in four papers. The first one provides a PAC bound for the L generalization error of methods based on combining regression procedures. This bound is tight to the...
متن کاملune approche PAC-Bayésienne PAC-Bayesian Statistical Learning Theory
This PhD thesis is a mathematical study of the learning task – specifically classification and least square regression – in order to better understand why an algorithm works and to propose more efficient procedures. The thesis consists in four papers. The first one provides a PAC bound for the L generalization error of methods based on combining regression procedures. This bound is tight to the...
متن کامل