Generalization Error Bounds for Learning under Censored Feedback

arXiv:2404.09247v1 Announce Type: new
Abstract: Generalization error bounds from learning theory provide statistical guarantees on how well an algorithm will perform on previously unseen data. In this paper, we characterize the impacts of data non-IIDness due to censored feedback (a.k.a. selective labeling bias) on such bounds. We first derive an extension of the well-known Dvoretzky-Kiefer-Wolfowitz (DKW) inequality, which characterizes the gap between empirical and theoretical CDFs given IID data, to problems with non-IID data due to censored feedback. We then …

abstract algorithm arxiv bias cs.lg data error extension feedback impacts labeling paper statistical stat.ml theory type will