2 papers
cs.LG2026
Sinkhorn-Drifting Generative Models
Ping He, Om Khangaonkar, Hamed Pirsiavash +2
We establish a theoretical link between the recently proposed "drifting" generative dynamics and gradient flows induced by the Sinkhorn divergence. In a particle discretization, th…
cs.LG2025
Fused Partial Gromov-Wasserstein for Structured Objects
Yikun Bai, Shuang Wang, Huy Tran +3
Structured data, such as graphs, is vital in machine learning due to its capacity to capture complex relationships and interactions. In recent years, the Fused Gromov-Wasserstein (…