A contact-geometry reformulation of the Schrödinger bridge allows energy-varying paths and is solved as a non-iterative ResNet geodesic on the Wasserstein manifold.
Lars Ruthotto, Stanley J Osher, Wuchen Li, Levon Nurbekyan, and Samy Wu Fung
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Neural surrogates enable a four-stage alternating algorithm for nonlocal mean-field Schrödinger bridges with linear scaling and Gronwall stability bounds.
citing papers explorer
-
Nonlocal Mean Field Schr\"{o}dinger Bridge with Learned Interactions
Neural surrogates enable a four-stage alternating algorithm for nonlocal mean-field Schrödinger bridges with linear scaling and Gronwall stability bounds.