Iterative regularization in classification via hinge loss diagonal descent
This work addresses classification problems by providing a stable and efficient iterative regularization method, though it appears incremental as it builds on existing regularization theory.
The paper tackles iterative regularization for classification by developing a hinge loss diagonal descent algorithm, proving convergence rates and stability under a classification noise model, and showing favorable performance in numerical simulations.
Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of linear inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence and stability results for a suitable classification noise model. Our approach compares favorably with other alternatives, as confirmed by numerical simulations.