Minimax nonparametric classification. II. Model selection for adaptation
[For part I of this paper see the preceding entry, Zbl 0962.62026).] We study nonparametric estimation of a conditional probability for classification based on a collection of finite-dimensional models. For the sake of flexibility, different types of models, linear or nonlinear, are allowed as long as each satisfies a dimensionality assumption. We show that with a suitable model selection criterion, the penalized maximum-likelihood estimator has risk bounded by an index of resolvability expressing a good tradeoff among approximation error, estimation error, and model complexity. The bound does not require any assumption on the target conditional probability and can be used to demonstrate the adaptivity of estimators based on model selection. Examples are given with both splines and neural nets, and problems of high-dimensional estimation are considered. The resulting adaptive estimator is shown to behave optimally or near optimally over Sobolev classes (with unknown orders of interaction and smoothness) and classes of integrable Fourier transforms of gradients. In terms of rates of convergence, performance is the same as if one knew which of them contains the true couditional probability in advance. The corresponding classifier also converges optimally or nearly optimally simultaneously over these classes.
- Convergence rates of generalization errors for margin-based classification
- On Strong Consistency of Model Selection in Classification
- Bandwidth choice for nonparametric classification
- Classification with minimax fast rates for classes of Bayes rules with sparse representation
- Asymptotic frequentist coverage properties of Bayesian credible sets for sieve priors
- A nonparametric ensemble binary classifier and its statistical properties
- Minimax optimal rates of convergence for multicategory classifications
- Optimal rates of aggregation in classification under low noise assumption
- Square root penalty: Adaption to the margin in classification and in edge estimation
- Transfer learning for nonparametric classification: minimax rate and adaptive classifier
- Optimal classification and nonparametric regression for functional data
- Theory of Classification: a Survey of Some Recent Advances
- Minimax nonparametric classification .I. Rates of convergence
- Adaptive model selection for digital linear classifiers
- Review on functional data classification
- Functional data analysis using deep neural networks
This page was built for publication: Minimax nonparametric classification. II. Model selection for adaptation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4503439)