Hostname: page-component-7b7567c8c-wxvwp Total loading time: 0 Render date: 2026-11-18T14:55:18.069Z Has data issue: false hasContentIssue false

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

Published online by Cambridge University Press:  20 July 2017

NICOLÁS GARCÍA TRILLOS
Affiliation:
Division of Applied Mathematics, Brown University, Providence, RI, 02912, USA email: nicolas_garcia_trillos@brown.edu
RYAN MURRAY
Affiliation:
Mathematics Department, The Pennsylvania State University, University Park, PA 16802, USA email: rwm22@psu.edu
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

This work considers the problem of binary classification: given training data x 1, . . ., x n from a certain population, together with associated labels y 1,. . ., y n ∈ {0,1}, determine the best label for an element x not 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.

Information

Type
Papers
Creative Commons
This is a work of the U.S. Government and is not subject to copyright protection in the United States.
Copyright
Copyright © Cambridge University Press 2017