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.
On the surrogate gap between contrastive and supervised losses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 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.