Generative Adversarial Network: Some Analytical Perspectives
It provides theoretical insights into GANs for researchers in machine learning and applied mathematics, but is incremental as it reviews and extends existing analytical approaches.
The paper examines generative adversarial networks (GANs) from analytical perspectives, addressing performance and training issues, and discusses their applications in high-dimensional mean-field games and mathematical finance problems.
Ever since its debut, generative adversarial networks (GANs) have attracted tremendous amount of attention. Over the past years, different variations of GANs models have been developed and tailored to different applications in practice. Meanwhile, some issues regarding the performance and training of GANs have been noticed and investigated from various theoretical perspectives. This subchapter will start from an introduction of GANs from an analytical perspective, then move on to the training of GANs via SDE approximations and finally discuss some applications of GANs in computing high dimensional MFGs as well as tackling mathematical finance problems.