A new unbalanced optimal transport formulation with Gromov-Wasserstein marginal penalties computes joint embeddings of heterogeneous datasets into a common metric space and provably converges to the embedded Wasserstein distance as the penalty grows.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Joint Metric Space Embedding by Unbalanced OT with Gromov-Wasserstein Marginal Penalization
A new unbalanced optimal transport formulation with Gromov-Wasserstein marginal penalties computes joint embeddings of heterogeneous datasets into a common metric space and provably converges to the embedded Wasserstein distance as the penalty grows.