Highly over-parameterized classifiers generalize since bad solutions are rare

We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many global minima with zero training error, some of which generalize better than others. We show that under certain conditions the fraction of "bad" global minima with a true error larger than {\epsilon} decays to zero exponentially fast with the number of training data n. The bound depends on the distribution of the true error over the set of classifier functions used for the given classification problem, and does not necessarily depend on the size or complexity (e.g. the number of parameters) of the classifier function set. This might explain the unexpectedly good generalization even of highly over-parameterized Neural Networks. We validate our mathematical framework with experiments on a synthetic data set and a subset of MNIST, and also test our hypothesis with VGG19 and ResNet18 on a subset of Caltech101.