AI RESEARCH
Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
arXiv CS.LG
•
ArXi:2605.28767v1 Announce Type: new Many real-world classification tasks require predicting multiple labels per instance, necessitating the optimization of complex evaluation metrics such as the $F$-measure and Jaccard index. While the Empirical Utility Maximization (EUM) framework is natural for these population-level metrics, existing theoretical results are largely limited to asymptotic Bayes-consistency.