New variance-reduced bag-level losses bring the sample complexity of LLP under square loss down to k/β (realizable) and k/β² (non-realizable), with a lower bound showing linear dependence on bag size is necessary.
Supervised learning by training on aggregate outputs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Nearly Optimal Sample Complexity for Learning with Label Proportions
New variance-reduced bag-level losses bring the sample complexity of LLP under square loss down to k/β (realizable) and k/β² (non-realizable), with a lower bound showing linear dependence on bag size is necessary.