Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.
Y ., Klein, M., and Cu- turi, M
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
RLDT fine-tunes pretrained flow-matching policies for continuous control by aligning them to a max-entropy RL transport field constructed via SVGD, using expected-target estimation for stable multi-step updates.
By designing the prior as the low-frequency projection of data images, flow matching achieves OT-optimal identity couplings without explicit OT computation, reducing trajectory curvature over 2x and improving few-step quality.
The expected minibatch OT plan converges to the true OT plan with quantifiable bias and convergence rates, yielding a regular velocity field for unique flows from source to discrete target in flow matching.
Introduces Wasserstein-on-Wasserstein flow matching that realizes metameasure flows via nested Wasserstein geometry and scalable sliced/linear approximations for generative modeling of transport plans.
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
citing papers explorer
-
Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization
Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.