Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting

arXiv:2404.07083v1 Announce Type: new
Abstract: Overparameterized deep neural networks (DNNs), if not sufficiently regularized, are susceptible to overfitting their training examples and not generalizing well to test data. To discourage overfitting, researchers have developed multicomponent loss functions that reduce intra-class feature correlation and maximize inter-class feature distance in one or more layers of the network. By analyzing the penultimate feature layer activations output by a DNN's feature extraction section prior to the linear classifier, we find that modified forms of …

arxiv cs.lg overfitting risk type