17
0

GRASP: A Goodness-of-Fit Test for Classification Learning

Abstract

Performance of classifiers is often measured in terms of average accuracy on test data. Despite being a standard measure, average accuracy fails in characterizing the fit of the model to the underlying conditional law of labels given the features vector (YXY|X), e.g. due to model misspecification, over fitting, and high-dimensionality. In this paper, we consider the fundamental problem of assessing the goodness-of-fit for a general binary classifier. Our framework does not make any parametric assumption on the conditional law YXY|X, and treats that as a black box oracle model which can be accessed only through queries. We formulate the goodness-of-fit assessment problem as a tolerance hypothesis testing of the form \[ H_0: \mathbb{E}\Big[D_f\Big({\sf Bern}(\eta(X))\|{\sf Bern}(\hat{\eta}(X))\Big)\Big]\leq \tau\,, \] where DfD_f represents an ff-divergence function, and η(x)\eta(x), η^(x)\hat{\eta}(x) respectively denote the true and an estimate likelihood for a feature vector xx admitting a positive label. We propose a novel test, called \grasp for testing H0H_0, which works in finite sample settings, no matter the features (distribution-free). We also propose model-X \grasp designed for model-X settings where the joint distribution of the features vector is known. Model-X \grasp uses this distributional information to achieve better power. We evaluate the performance of our tests through extensive numerical experiments.

View on arXiv
Comments on this paper