弱监督分类的下界真损失
Lower-Bounded Proper Losses for Weakly Supervised Classification
摘要：
本文讨论了弱监督分类问题，其中实例被赋予由一些标签腐败过程产生的弱标签。我们的目标是推导出弱标签学习的损失函数是适当的和下界的条件-这是类概率估计中使用的损失的两个基本要求。为此，我们推导出监督学习中适当损失的表示定理，它使Savage表示二元化。我们使用这个定理来刻画适当的弱标签损失，并找到一个条件，他们是下界。从这些理论发现中，我们得到了一个新的正则化方案，称为广义logit压缩，它使任何适当的弱标签损失从下有界，而不会失去适当性。此外，我们通过实验证明了我们所提出的方法的有效性，相比不适当的或无界的损失。结果突出了适当性和下界的重要性。
英文摘要：
This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label learning are proper and lower-bounded -- two essential requirements for the losses used in class-probability estimation. To this end, we derive a representation theorem for proper losses in supervised learning, which dualizes the Savage representation. We use this theorem to characterize proper weak-label losses and find a condition for them to be lower-bounded. From these theoretical findings, we derive a novel regularization scheme called generalized logit squeezing, which makes any proper weak-label loss bounded from below, without losing properness. Furthermore, we experimentally demonstrate the effectiveness of our proposed approach, as compared to improper or unbounded losses. The results highlight the importance of properness and lower-boundedness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
