An augmentation-aware error bound for contrastive learning decomposes the augmentation gap into a minimum same-class distance and a maximum same-image distance, with a trade-off driven by augmentation strength.
A theoretical analysis of contrastive unsupervised representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
An augmentation-aware error bound for contrastive learning decomposes the augmentation gap into a minimum same-class distance and a maximum same-image distance, with a trade-off driven by augmentation strength.