A new analytical approach to consistency and overfitting in regularized empirical risk minimization
This work provides a theoretical framework for understanding overfitting and consistency in machine learning, which is incremental as it builds on existing regularization methods with new analytical insights.
The paper tackles the problem of binary classification by analyzing a variant of regularized empirical risk minimization that is data-dependent, using modern analytical tools to prove asymptotic consistency as regularization parameters approach zero at sample-dependent rates, and connecting overfitting to a loss of compactness.
This work considers the problem of binary classification: given training data $x_1, \dots, x_n$ from a certain population, together with associated labels $y_1,\dots, y_n \in \left\{0,1 \right\}$, 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.