通过单变量损失的一致多标签排序
Consistent Multilabel Ranking through Univariate Losses
摘要：
我们考虑多标签分类中的秩损失最小化问题，这通常是通过定义在标签对上的凸代理损失来解决的。最近，这种方法受到质疑，一个负面的结果表明，常用的成对替代损失，如指数和逻辑损失，是不一致的。在本文中，我们展示了一个积极的结果，这可以说是令人惊讶的，鉴于前一个：更简单的单变量的指数和逻辑代理（即，定义在单个标签上）对于秩损失最小化是一致的。而不是直接证明收敛性，我们给出了一个更强大的结果，通过推导遗憾界和收敛速度。建议的损失建议有效的和可扩展的算法，这是实验测试。
英文摘要：
We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labels. Very recently, this approach was put into question by a negative result showing that commonly used pairwise surrogate losses, such as exponential and logistic losses, are inconsistent. In this paper, we show a positive result which is arguably surprising in light of the previous one: the simpler univariate variants of exponential and logistic surrogates (i.e., defined on single labels) are consistent for rank loss minimization. Instead of directly proving convergence, we give a much stronger result by deriving regret bounds and convergence rates. The proposed losses suggest efficient and scalable algorithms, which are tested experimentally.
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。
