Is Transductive Learning Equivalent to PAC Learning?

arXiv:2405.05190v1 Announce Type: cross
Abstract: Most work in the area of learning theory has focused on designing effective Probably Approximately Correct (PAC) learners. Recently, other models of learning such as transductive error have seen more scrutiny. We move toward showing that these problems are equivalent by reducing agnostic learning with a PAC guarantee to agnostic learning with a transductive guarantee by adding a small number of samples to the dataset. We first rederive the result of Aden-Ali et al. arXiv:2304.09167 …

abstract arxiv cs.ds cs.lg designing error math.st stat.ml stat.th theory type work