NONPARAMETRIC-ESTIMATION VIA EMPIRICAL RISK MINIMIZATION

被引：115

作者：

LUGOSI, G ^{[1
]}

ZEGER, K ^{[1
]}

机构：

[1] UNIV ILLINOIS,DEPT ELECT & COMP ENGN,COORDINATED SCI LAB,URBANA,IL 61801

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1995年 / 41卷 / 03期

基金：

美国国家科学基金会;

关键词：

REGRESSION ESTIMATION; NONPARAMETRIC ESTIMATION; CONSISTENCY; PATTERN RECOGNITION; NEURAL NETWORKS; SERIES METHODS; SIEVES;

D O I：

10.1109/18.382014

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A general notion of universal consistency of nonparametric estimators is introduced that applies to regression estimation, conditional median estimation, curve fitting, pattern recognition, and learning concepts. General methods for proving consistency of estimators based on minimizing the empirical error are shown, In particular, distribution-free almost sure consistency of neural network estimates and generalized linear estimators is established.

引用

页码：677 / 687

页数：11

共 50 条

[31] Multivariate, heteroscedastic empirical Bayes via nonparametric maximum likelihood [J].

Soloff, Jake A. ;

Guntuboyina, Adityanand ;

Sen, Bodhisattva .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2024, 87 (01) :1-32

[32] EFFICIENCY OF CLASSIFICATION METHODS BASED ON EMPIRICAL RISK MINIMIZATION [J].

Norkin, V. I. ;

Keyzer, M. A. .

CYBERNETICS AND SYSTEMS ANALYSIS, 2009, 45 (05) :750-761

[33] Consistency of empirical risk minimization for unbounded loss functions [J].

Muselli, Marco ;

Ruffino, Francesca .

Biological and Artificial Intelligence Environments, 2005, :261-270

[34] Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization [J].

Daunas, Francisco ;

Esnaola, Inaki ;

Perlaza, Samir M. ;

Vincent Poor, H. .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2025, 71 (08) :6198-6226

[35] Deep empirical risk minimization in finance: Looking into the future [J].

Reppen, Anders Max ;

Soner, Halil Mete .

MATHEMATICAL FINANCE, 2023, 33 (01) :116-145

[36] Adaptive nonparametric instrumental variables estimation: Empirical choice of the regularization parameter [J].

Horowitz, Joel L. .

JOURNAL OF ECONOMETRICS, 2014, 180 (02) :158-173

[37] Nonparametric estimation of the ROC curve based on smoothed empirical distribution functions [J].

Jokiel-Rokita, Alicja ;

Pulit, Micha .

STATISTICS AND COMPUTING, 2013, 23 (06) :703-712

[38] Nonparametric estimation of the ROC curve based on smoothed empirical distribution functions [J].

Alicja Jokiel-Rokita ;

Michał Pulit .

Statistics and Computing, 2013, 23 :703-712

[39] Nonparametric estimation of the ruin probability for generalized risk processes [J].

Bening, VE ;

Korolev, VY .

THEORY OF PROBABILITY AND ITS APPLICATIONS, 2002, 47 (01) :1-16

[40] Nonparametric estimation of risk tracking indices for longitudinal studies [J].

Wu, Colin O. ;

Tian, Xin ;

Tian, Lu ;

Reis, Jared P. ;

Zhao, Lihui ;

Allen, Norrina B. ;

Bae, Sejong ;

Liu, Kiang .

STATISTICAL METHODS IN MEDICAL RESEARCH, 2020, 29 (02) :481-497

← 1 2 3 4 5 →