Durrant, R. J., & Kaban, A. (2013). Sharp generalization error bounds for randomly-projected classifiers. In S. Dasgupta & D. McAllester (Eds.), Proceedings of the Thirtieth International Conference on Machine Learning, Atlanta, USA(Vol. JMLR Workshop and Conference Proceedings, Volume 28, p. 693).
Permanent Research Commons link: https://hdl.handle.net/10289/8941
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 .
This is an author’s accepted version of a paper published in the Proceedings of The 30th International Conference on Machine Learning. © 2013 The Authors.