Self-supervised learning can be understood as latent distribution matching, and under a Gaussian predictive model this yields identifiable representations up to affine transformations.
Lifting archi- tectural constraints of injective flows.arXiv preprint arXiv:2306.01843
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding Self-Supervised Learning via Latent Distribution Matching
Self-supervised learning can be understood as latent distribution matching, and under a Gaussian predictive model this yields identifiable representations up to affine transformations.