Classification using margin pursuit
[edit]
Proceedings of Machine Learning Research, PMLR 89:712720, 2019.
Abstract
In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers, in which the learner searches the hypothesis space in such a way that a preset margin level ends up being a distributionrobust estimator of the margin location. This procedure is easily implemented using gradient descent, and admits finitesample bounds on the excess risk under unbounded inputs, yielding competitive rates under mild assumptions. Empirical tests on realworld benchmark data reinforce the basic principles highlighted by the theory.
Related Material


