A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
arXiv preprint arXiv:2402.06162 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Equivariant SGMs achieve improved Wasserstein-1 generalization bounds on group-invariant distributions and learn the symmetrized score via equivariant vector fields without augmentation, with non-equivariant models incurring a quantifiable model-form error.
citing papers explorer
-
Fixed-Point Neural Optimal Transport without Implicit Differentiation
A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
-
Equivariant score-based generative models provably learn distributions with symmetries efficiently
Equivariant SGMs achieve improved Wasserstein-1 generalization bounds on group-invariant distributions and learn the symmetrized score via equivariant vector fields without augmentation, with non-equivariant models incurring a quantifiable model-form error.