CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants
We study the recovery of forward and reverse quadratic optimal-transport maps from unpaired samples in high dimensions. We introduce a bidirectional neural framework in which the learned maps induce forward and backward displacement interpolants, while the training objective combines bidirectional quadratic action, dis...
Shi-Zhou Xu, Jia-Chen Liu, Shih-Hsin Wang et al.
· 0 citations