Generative Adversarial Network: Some Analytical Perspectives
- URL: http://arxiv.org/abs/2104.12210v1
- Date: Sun, 25 Apr 2021 17:12:32 GMT
- Title: Generative Adversarial Network: Some Analytical Perspectives
- Authors: Haoyang Cao and Xin Guo
- Abstract summary: generative adversarial networks (GANs) have attracted tremendous amount of attention.
Different variations of GANs models have been developed and tailored to different applications in practice.
Issues regarding the performance and training of GANs have been noticed and investigated from various theoretical perspectives.
- Score: 4.933916728941277
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 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.
Related papers
- On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks [56.78271181959529]
Kolmogorov--Arnold Networks (KANs) have gained significant attention in the deep learning community.
Empirical investigations demonstrate that KANs optimized via gradient descent (SGD) are capable of achieving near-zero training loss.
arXiv Detail & Related papers (2024-10-10T15:34:10Z) - Deep Graph Anomaly Detection: A Survey and New Perspectives [86.84201183954016]
Graph anomaly detection (GAD) aims to identify unusual graph instances (nodes, edges, subgraphs, or graphs)
Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD.
arXiv Detail & Related papers (2024-09-16T03:05:11Z) - A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes [49.32130498861987]
We study the case of non-differentiable activation functions, such as ReLU.
Two recent works introduced a geometric framework to study neural networks.
We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
arXiv Detail & Related papers (2024-04-09T08:11:46Z) - A Chronological Survey of Theoretical Advancements in Generative
Adversarial Networks for Computer Vision [0.0]
Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision.
There have been many surveys on GANs, organizing the vast GAN literature from various focus and perspectives.
This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order.
arXiv Detail & Related papers (2023-11-02T05:11:47Z) - Ten Years of Generative Adversarial Nets (GANs): A survey of the
state-of-the-art [0.0]
Generative Adversarial Networks (GANs) have rapidly emerged as powerful tools for generating realistic and diverse data across various domains.
In February 2018, GAN secured the leading spot on the Top Ten Global Breakthrough Technologies List''
This survey aims to provide a general overview of GANs, summarizing the latent architecture, validation metrics, and application areas of the most widely recognized variants.
arXiv Detail & Related papers (2023-08-30T20:46:45Z) - Generative Adversarial Networks for Image Super-Resolution: A Survey [101.39605080291783]
Single image super-resolution (SISR) has played an important role in the field of image processing.
Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples.
In this paper, we conduct a comparative study of GANs from different perspectives.
arXiv Detail & Related papers (2022-04-28T16:35:04Z) - Fine-Grained Image Analysis with Deep Learning: A Survey [146.22351342315233]
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition.
This paper attempts to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval.
arXiv Detail & Related papers (2021-11-11T09:43:56Z) - A Survey on Generative Adversarial Networks: Variants, Applications, and
Training [9.299132423767992]
Generative Adversarial Networks (GAN) have gained considerable attention in the field of unsupervised learning.
Despite GAN's excellent success, there are still obstacles to stable training.
Herein, we survey several training solutions proposed by different researchers to stabilize GAN training.
arXiv Detail & Related papers (2020-06-09T09:04:41Z) - Regularization Methods for Generative Adversarial Networks: An Overview
of Recent Studies [3.829070379776576]
Generative Adversarial Network (GAN) has been extensively studied and used for various tasks.
Regularization methods have been proposed to make the training of GAN stable.
arXiv Detail & Related papers (2020-05-19T01:59:24Z) - A Review on Generative Adversarial Networks: Algorithms, Theory, and
Applications [154.4832792036163]
Generative adversarial networks (GANs) are a hot research topic recently.
GANs have been widely studied since 2014, and a large number of algorithms have been proposed.
This paper provides a review on various GANs methods from the perspectives of algorithms, theory, and applications.
arXiv Detail & Related papers (2020-01-20T01:52:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.