Neural networks inspired by the Kuratowski embedding theorem approximate Wasserstein-2 distances on MNIST with lower error than baselines.
Wassmap: Wasserstein isometric mapping for image manifold learning.SIAM Journal on Mathematics of Data Science, 5(2):475–501, 2023
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
-
Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning
Neural networks inspired by the Kuratowski embedding theorem approximate Wasserstein-2 distances on MNIST with lower error than baselines.