Search Machine Learning Repository:
Sharp Generalization Error Bounds for Randomly-projected Classifiers
Authors: Robert Durrant and Ata Kaban
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
Abstract: We derive sharp bounds on the generalization error of a generic linear classifier trained by empirical risk minimization on randomly-projected data. We make no restrictive assumptions (such as sparsity or separability) on the data: Instead we use the fact that, in a classification setting, the question of interest is really `what is the effect of random projection on the predicted class labels?' and we therefore derive the exact probability of `label flipping' under Gaussian random projection in order to quantify this effect precisely in our bounds.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).