Develops H-consistent surrogate losses for generalized metrics in multi-label classification that decompose exactly in O(l) time and introduces the MMO family of algorithms.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
Develops H-consistent surrogate losses for generalized metrics in multi-label classification that decompose exactly in O(l) time and introduces the MMO family of algorithms.