Generative Adversarial Networks (GANs) is a novel class of deep generative models which has recently gained significant attention. GANs learns complex and high-dimensional distributions implicitly over images, audio, and data. However, there exists major challenges in training of GANs, i.e., mode collapse, non-convergence and instability, due to inappropriate design of network architecture, use of objective function and selection of optimization algorithm. Recently, to address these challenges, several solutions for better design and optimization of GANs have been investigated based on techniques of re-engineered network architectures, new objective functions and alternative optimization algorithms. To the best of our knowledge, there is no existing survey that has particularly focused on broad and systematic developments of these solutions. In this study, we perform a comprehensive survey of the advancements in GANs design and optimization solutions proposed to handle GANs challenges. We first identify key research issues within each design and optimization technique and then propose a new taxonomy to structure solutions by key research issues. In accordance with the taxonomy, we provide a detailed discussion on different GANs variants proposed within each solution and their relationships. Finally, based on the insights gained, we present the promising research directions in this rapidly growing field.

翻译：生成对抗网络（GANs）是一类新颖的深度生成模型，近年来受到广泛关注。GANs能够隐式地学习图像、音频和数据中复杂且高维的分布。然而，由于网络架构设计不当、目标函数使用不合理以及优化算法选择有误，GANs的训练存在重大挑战，即模式崩塌、不收敛和不稳定性。近年来，为应对这些挑战，研究人员基于网络架构重构、新型目标函数和替代优化算法等技术，探索了多种改进GANs设计与优化的解决方案。据我们所知，目前尚无综述专门系统性地全面梳理这些解决方案的发展。在本研究中，我们对针对GANs挑战所提出的设计与优化解决方案的进展进行了全面综述。我们首先识别出每种设计与优化技术中的关键研究问题，然后提出了一种新的分类法，按关键研究问题对解决方案进行结构化整理。依据该分类法，我们详细讨论了每种解决方案下提出的不同GANs变体及其相互关系。最后，基于所得见解，我们指出了这一快速发展的领域中具有前景的研究方向。