Generative Adversarial Network: Some Analytical Perspectives
arXiv:2104.12210
Abstract
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.
arXiv commentContributed to the book, "Machine Learning in Financial Markets: A Guide to Contemporary Practice", edited by Agostino Capponi and Charles-Albert Lehalle
References in corpus (16)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Generative Adversarial Text to Image Synthesis
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Which Training Methods for GANs do actually Converge?
- Semantic Segmentation using Adversarial Networks
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- Stabilizing Generative Adversarial Networks: A Survey
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
- Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
- Convergence Problems with Generative Adversarial Networks (GANs)
- Fluctuation-dissipation relations for stochastic gradient descent
- COT-GAN: Generating Sequential Data via Causal Optimal Transport
- The variational structure and time-periodic solutions for mean-field games systems
- Relaxed Wasserstein with Applications to GANs
- f-GANs in an Information Geometric Nutshell