Convergence of non-convex non-concave GANs using sinkhorn divergence

• المؤلفون الرئيسيون: Adnan, Risman, Saputra, Muchlisin Adi, Fadlil, Junaidillah, Ezerman, Martianus Frederic, Iqbal, Muhamad, Basaruddin, Tjan
• مؤلفون آخرون: School of Physical and Mathematical Sciences
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Science::Physics; Convergence; Generative Adversarial Network
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/154075

Sinkhorn divergence is a symmetric normalization of entropic regularized optimal transport. It is a smooth and continuous metrized weak-convergence with excellent geometric properties. We use it as an alternative for the minimax objective function in formulating generative adversarial networks. The...