Optimal Transport (OT) theory is utilized in generative modeling, with recent advancements focusing on OT-based generative models. These models face challenges like unstable training processes and limited expressivity. UOTM introduces a semi-dual form of Unbalanced Optimal Transport (UOT) problem, showing promising outcomes but lacking τ-robustness. A novel method, UOTM with Scheduled Divergence (UOTM-SD), gradually adjusts the divergence term to improve performance while addressing τ-sensitivity. The equi-Lipschitz continuity of UOTM potential contributes to stable convergence during training.
Sang ngôn ngữ khác
từ nội dung nguồn
arxiv.org
Thông tin chi tiết chính được chắt lọc từ
by Jaemoo Choi,... lúc arxiv.org 03-08-2024
https://arxiv.org/pdf/2310.02611.pdfYêu cầu sâu hơn