paper-with-me

홈 › Papers

Towards Distributed Coevolutionary GANs

2018-07-21 · Abdullah Al-Dujaili, Tom Schmiedlechner, and Erik Hemberg, Una-May O'Reilly

Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. Despite their demonstrated success on multiple vision tasks, GANs are difficult to train and much research has been dedicated towards understanding and improving their gradient-based learning dynamics. Here, we investigate the use of coevolution, a class of black-box (gradient-free) co-optimization techniques and a powerful tool in evolutionary computing, as a supplement to gradient-based GAN training techniques. Experiments on a simple model that exhibits several of the GAN gradient-based dynamics (e.g., mode collapse, oscillatory behavior, and vanishing gradients) show that coevolution is a promising framework for escaping degenerate GAN training behaviors.

📄 PDF Abstract BibTeX arXiv:1807.08194

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Parallel/distributed implementation of cellular training for generative adversarial neural networks

2020-04-07 · Emiliano Perez, Sergio Nesmachnow, Jamal Toutouh, Erik Hemberg 외

Generative adversarial networks (GANs) are widely used to learn generative models. GANs consist of two networks, a generator and a discriminator, that apply adversarial learning to optimize their parameters. This article…

Lipizzaner: A System That Scales Robust Generative Adversarial Network Training

2018-11-30 · Tom Schmiedlechner, Ignavier Ng Zhi Yong, Abdullah Al-Dujaili, Erik Hemberg 외

GANs are difficult to train due to convergence pathologies such as mode and discriminator collapse. We introduce Lipizzaner, an open source software system that allows machine learning engineers to train GANs in a distri…

Generative Adversarial Network

Multi-population GAN Training: Analyzing Co-Evolutionary Algorithms

2025-07-17 · Walter P. Casas, Jamal Toutouh

Generative adversarial networks (GANs) are powerful generative models but remain challenging to train due to pathologies suchas mode collapse and instability. Recent research has explored co-evolutionary approaches, in w…

DiversityEvolutionary Algorithms

Analyzing the Components of Distributed Coevolutionary GAN Training

2020-08-03 · Jamal Toutouh, Erik Hemberg, Una-May O'Reilly

Distributed coevolutionary Generative Adversarial Network (GAN) training has empirically shown success in overcoming GAN training pathologies. This is mainly due to diversity maintenance in the populations of generators …

DiversityGenerative Adversarial Network

Signal Propagation in a Gradient-Based and Evolutionary Learning System

2021-02-10 · Jamal Toutouh, Una-May O'Reilly

Generative adversarial networks (GANs) exhibit training pathologies that can lead to convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary algorithms (CEAs) for GAN training, e.g. Lipi…