Full-support von Mises-Fisher sampling satisfies a diversity condition allowing global contrastive loss minimizers to recover latent geometry up to orthogonal transformation, while restricted sampling permits non-orthogonal maps to achieve lower loss; a support-corrected InfoNCE is introduced.
A Probabilistic Generalization of the
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
-
The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
Full-support von Mises-Fisher sampling satisfies a diversity condition allowing global contrastive loss minimizers to recover latent geometry up to orthogonal transformation, while restricted sampling permits non-orthogonal maps to achieve lower loss; a support-corrected InfoNCE is introduced.