Skip to Main content Skip to Navigation

Plug-in methods in classification

Abstract : This manuscript studies several problems of constrained classification. In this frameworks of classification our goal is to construct an algorithm which performs as good as the best classifier that obeys some desired property. Plug-in type classifiers are well suited to achieve this goal. Interestingly, it is shown that in several setups these classifiers can leverage unlabeled data, that is, they are constructed in a semi-supervised manner.Chapter 2 describes two particular settings of binary classification -- classification with F-score and classification of equal opportunity. For both problems semi-supervised procedures are proposed and their theoretical properties are established. In the case of the F-score, the proposed procedure is shown to be optimal in minimax sense over a standard non-parametric class of distributions. In the case of the classification of equal opportunity the proposed algorithm is shown to be consistent in terms of the misclassification risk and its asymptotic fairness is established. Moreover, for this problem, the proposed procedure outperforms state-of-the-art algorithms in the field.Chapter 3 describes the setup of confidence set multi-class classification. Again, a semi-supervised procedure is proposed and its nearly minimax optimality is established. It is additionally shown that no supervised algorithm can achieve a so-called fast rate of convergence. In contrast, the proposed semi-supervised procedure can achieve fast rates provided that the size of the unlabeled data is sufficiently large.Chapter 4 describes a setup of multi-label classification where one aims at minimizing false negative error subject to almost sure type constraints. In this part two specific constraints are considered -- sparse predictions and predictions with the control over false negative errors. For the former, a supervised algorithm is provided and it is shown that this algorithm can achieve fast rates of convergence. For the later, it is shown that extra assumptions are necessary in order to obtain theoretical guarantees in this case
Document type :
Complete list of metadatas

Cited literature [164 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Monday, December 9, 2019 - 3:27:08 PM
Last modification on : Sunday, September 27, 2020 - 4:47:39 AM
Long-term archiving on: : Tuesday, March 10, 2020 - 9:08:59 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02400552, version 1



Evgenii Chzhen. Plug-in methods in classification. Optimization and Control [math.OC]. Université Paris-Est, 2019. English. ⟨NNT : 2019PESC2027⟩. ⟨tel-02400552⟩



Record views


Files downloads