Analysis of Nonautonomous Adversarial Systems

2018/03/13 by Arash Mehrjou, Mehrjou, Arash · 1 citation
Computer Science · #Advanced Image Processing Techniques #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1803.05045

openalex publication_date 2018/03/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Generative adversarial networks are used to generate images but still their convergence properties are not well understood. There have been a few studies who intended to investigate the stability properties of GANs as a dynamical system. This short writing can be seen in that direction. Among the proposed methods for stabilizing training of GANs, ß-GAN was the first who proposed a complete annealing strategy to change high-level conditions of the GAN objective. In this note, we show by a simple example how annealing strategy works in GANs. The theoretical analysis is supported by simple simulations.

Citations

• Annealed Generative Adversarial Networks

Cited by

• Distribution Aware Active Learning

Related

• Smoothness and Stability in GANs
• Annealed Generative Adversarial Networks
• Stabilizing Generative Adversarial Networks: A Survey
• A Survey on Generative Adversarial Networks: Variants, Applications, and\n Training
• Towards a Better Understanding and Regularization of GAN Training Dynamics