The paper proves statistical consistency of contrastive loss to optimal ranking via an AUC criterion and derives generalization bounds O(1/m + 1/sqrt(n)) for supervised and O(1/sqrt(m) + 1/sqrt(n)) for self-supervised CRL that explain benefits of large negative sets.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
MetaEns trains on meta-datasets to predict marginal gains from adding models and uses a submodular-inspired objective with diversity discounting and risk regularization for greedy unsupervised ensemble selection, outperforming baselines on 39 datasets.
Machine learning research should prioritize ideas by testing their predicted behavioral signatures in modern models through custom experiments instead of leaderboard chasing or abstract theorems.
citing papers explorer
-
Statistical Consistency and Generalization of Contrastive Representation Learning
The paper proves statistical consistency of contrastive loss to optimal ranking via an AUC criterion and derives generalization bounds O(1/m + 1/sqrt(n)) for supervised and O(1/sqrt(m) + 1/sqrt(n)) for self-supervised CRL that explain benefits of large negative sets.
-
Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version
MetaEns trains on meta-datasets to predict marginal gains from adding models and uses a submodular-inspired objective with diversity discounting and risk regularization for greedy unsupervised ensemble selection, outperforming baselines on 39 datasets.