arxivst stuff from arxiv that you should probably bookmark

MAGAN: Margin Adaptation for Generative Adversarial Networks

Abstract · Apr 12, 2017 16:15 ·

synthetic gans training generator loss energy hinge generative discriminator margin cs-lg stat-ml

Arxiv Abstract

  • Ruohan Wang
  • Antoine Cully
  • Hyung Jin Chang
  • Yiannis Demiris

We propose a novel training procedure for Generative Adversarial Networks (GANs) to improve stability and performance by using an adaptive hinge loss objective function. We estimate the appropriate hinge loss margin with the expected energy of the target distribution, and derive both a principled criterion for updating the margin and an approximate convergence measure. The resulting training procedure is simple yet robust on a diverse set of datasets. We evaluate the proposed training procedure on the task of unsupervised image generation, noting both qualitative and quantitative performance improvements.

Read the paper (pdf) »