Simplified and Unified Analysis of Various Learning Problems by Reduction to Multiple-Instance Learning. (arXiv:1911.05999v4 [cs.LG] UPDATED)

In statistical learning, many problem formulations have been proposed so far,
such as multi-class learning, complementarily labeled learning, multi-label
learning, multi-task learning, which provide theoretical models for various
real-world tasks. Although they have been extensively studied, the relationship
among them has not been fully investigated. In this work, we focus on a
particular problem formulation called Multiple-Instance Learning (MIL), and
show that various learning problems including all the problems mentioned above
with some of new problems can be reduced to …

analysis arxiv learning lg simplified