A new analytical approach to consistency and overfitting in regularized empirical risk minimization

Nicolás García Trillos, Ryan Murray

Research output: Contribution to journalArticle

5 Scopus citations

Abstract

This work considers the problem of binary classification: given training data x1,., xn from a certain population, together with associated labels y1,., yn € {0,1}, determine the best label for an element xnot among the training data. More specifically, this work considers a variant of the regularized empirical risk functional which is defined intrinsically to the observed data and does not depend on the underlying population. Tools from modern analysis are used to obtain a concise proof of asymptotic consistency as regularization parameters are taken to zero at rates related to the size of the sample. These analytical tools give a new framework for understanding overfitting and underfitting, and rigorously connect the notion of overfitting with a loss of compactness.

Original languageEnglish (US)
Pages (from-to)886-921
Number of pages36
JournalEuropean Journal of Applied Mathematics
Volume28
Issue number6
DOIs
StatePublished - Dec 1 2017

All Science Journal Classification (ASJC) codes

  • Applied Mathematics

Fingerprint Dive into the research topics of 'A new analytical approach to consistency and overfitting in regularized empirical risk minimization'. Together they form a unique fingerprint.

  • Cite this