中文
相关论文

相关论文: Local Convergence of Gradient Descent-Ascent for T…

200 篇论文

Generative Adversarial Networks (GANs) are a widely-used tool for generative modeling of complex data. Despite their empirical success, the training of GANs is not fully understood due to the min-max optimization of the generator and…

机器学习 · 计算机科学 2022-08-23 Evan Becker , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

Generative Adversarial Networks (GANs) have become predominant in image generation tasks. Their success is attributed to the training regime which employs two models: a generator G and discriminator D that compete in a minimax zero sum…

机器学习 · 计算机科学 2020-11-25 Ariel Ruiz-Garcia , Ibrahim Almakky , Vasile Palade , Luke Hicks

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

机器学习 · 统计学 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Local SGD is a promising approach to overcome the communication overhead in distributed learning by reducing the synchronization frequency among worker nodes. Despite the recent theoretical advances of local SGD in empirical risk…

机器学习 · 计算机科学 2021-03-01 Yuyang Deng , Mehrdad Mahdavi

Fitting neural networks often resorts to stochastic (or similar) gradient descent which is a noise-tolerant (and efficient) resolution of a gradient descent dynamics. It outputs a sequence of networks parameters, which sequence evolves…

机器学习 · 统计学 2021-04-15 Gabriel Turinici

Generative adversarial networks (GANs) are designed with the help of min-max optimization problems that are solved with stochastic gradient-type algorithms which are known to be non-robust. In this work we revisit a non-adversarial method…

机器学习 · 计算机科学 2018-11-26 Kalliopi Basioti , George V. Moustakides , Emmanouil Z. Psarakis

A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of the model exceeds a certain threshold. A large body of work in…

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

机器学习 · 计算机科学 2021-10-12 Yi-Lun Wu , Hong-Han Shuai , Zhi-Rui Tam , Hong-Yu Chiu

Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the…

机器学习 · 计算机科学 2019-02-12 Hoang Thanh-Tung , Truyen Tran , Svetha Venkatesh

The Generative Adversarial Network (GAN) was recently introduced in the literature as a novel machine learning method for training generative models. It has many applications in statistics such as nonparametric clustering and nonparametric…

机器学习 · 统计学 2023-06-26 Sehwan Kim , Qifan Song , Faming Liang

Many modern machine learning algorithms such as generative adversarial networks (GANs) and adversarial training can be formulated as minimax optimization. Gradient descent ascent (GDA) is the most commonly used algorithm due to its…

机器学习 · 计算机科学 2022-07-01 Huan He , Shifan Zhao , Yuanzhe Xi , Joyce C Ho , Yousef Saad

Generative Adversarial Networks (GANs) have demonstrated unprecedented success in various image generation tasks. The encouraging results, however, come at the price of a cumbersome training process, during which the generator and…

计算机视觉与模式识别 · 计算机科学 2021-06-17 Chengchao Shen , Youtan Yin , Xinchao Wang , Xubin Li , Jie Song , Mingli Song

Gradient Descent Ascent (GDA) methods are the mainstream algorithms for minimax optimization in generative adversarial networks (GANs). Convergence properties of GDA have drawn significant interest in the recent literature. Specifically,…

最优化与控制 · 数学 2022-07-05 Haochuan Li , Farzan Farnia , Subhro Das , Ali Jadbabaie

Global probabilistic inversion within the latent space learned by a Generative Adversarial Network (GAN) has been recently demonstrated. Compared to inversion on the original model space, using the latent space of a trained GAN can offer…

地球物理 · 物理学 2020-01-29 Eric Laloy , Niklas Linde , Cyprien Ruffino , Romain Hérault , Gilles Gasso , Diedrik Jacques

Generative Adversarial Networks (GANs) are a powerful class of generative models in the deep learning community. Current practice on large-scale GAN training utilizes large models and distributed large-batch training strategies, and is…

最优化与控制 · 数学 2020-10-21 Mingrui Liu , Wei Zhang , Youssef Mroueh , Xiaodong Cui , Jerret Ross , Tianbao Yang , Payel Das

Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine…

机器学习 · 计算机科学 2018-07-02 Samuel A. Barnett

Abstract Generative adversarial networks (GANs) have achieved impressive performance in data synthesis and have driven the development of many applications. However, GANs are known to be hard to train due to their bilevel objective, which…

机器学习 · 计算机科学 2022-11-22 Yu-Rong Zhang , Ruei-Yang Su , Sheng Yen Chou , Shan-Hung Wu

In this paper, we study a large-scale multi-agent minimax optimization problem, which models many interesting applications in statistical learning and game theory, including Generative Adversarial Networks (GANs). The overall objective is a…

机器学习 · 计算机科学 2023-06-07 Zhenyu Sun , Ermin Wei

Training generative adversarial networks (GAN) in a distributed fashion is a promising technology since it is contributed to training GAN on a massive of data efficiently in real-world applications. However, GAN is known to be difficult to…

机器学习 · 计算机科学 2020-10-27 Xiaojun Chen , Shu Yang , Li Shen , Xuanrong Pang

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…

神经与进化计算 · 计算机科学 2018-09-05 Abdullah Al-Dujaili , Tom Schmiedlechner , and Erik Hemberg , Una-May O'Reilly
‹ 上一页 1 2 3 10 下一页 ›