In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors

Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy

We propose to study the generalization error of a learned predictor $\hat{h}$ in terms of that of a surrogate (potentially randomized) predictor that is coupled to $\hat{h}$ and desi…