English
Related papers

Related papers: Training Wasserstein GANs without gradient penalti…

200 papers

Within a broad class of generative adversarial networks, we show that discriminator optimization process increases a lower bound of the dual cost function for the Wasserstein distance between the target distribution $p$ and the generator…

Machine Learning · Statistics 2023-08-09 Akinori Tanaka

Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution. Recent studies have proposed stabilizing the training process for the WGAN and implementing the Lipschitz…

Machine Learning · Computer Science 2018-10-08 Cheolhyeong Kim , Seungtae Park , Hyung Ju Hwang

In this paper, we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function. We show that GANs without restriction on the…

Machine Learning · Computer Science 2019-06-25 Zhiming Zhou , Jiadong Liang , Yuxuan Song , Lantao Yu , Hongwei Wang , Weinan Zhang , Yong Yu , Zhihua Zhang

In this paper, we introduce a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transform theory,…

Computer Vision and Pattern Recognition · Computer Science 2018-07-17 Qingsong Yang , Pingkun Yan , Yanbo Zhang , Hengyong Yu , Yongyi Shi , Xuanqin Mou , Mannudeep K. Kalra , Ge Wang

Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it does not always outperform other variants of GANs. This is…

Machine Learning · Computer Science 2021-01-13 Minkai Xu , Zhiming Zhou , Guansong Lu , Jian Tang , Weinan Zhang , Yong Yu

We propose an alternative to the standard GAN training approach, in which the discriminator is a binary classifier trained by cross-entropy to distinguish real samples from generated ones. Instead, we directly target the discrimination…

Machine Learning · Computer Science 2026-05-13 Mohammadreza Tavasoli Naeini , Ali Bereyhi , Morteza Noshad , Ben Liang , Alfred O. Hero

We provide a framework to approximate the 2-Wasserstein distance and the optimal transport map, amenable to efficient training as well as statistical and geometric analysis. With the quadratic cost and considering the Kantorovich dual form…

Optimization and Control · Mathematics 2019-02-20 Amirhossein Taghvaei , Amin Jalali

The use of optimal transport cost for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGAN). Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal…

Machine Learning · Statistics 2024-04-04 Antoine Houdard , Arthur Leclaire , Nicolas Papadakis , Julien Rabin

We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commonly used in existing approaches. Our key idea is to parameterize a single potential in the…

Optimization and Control · Mathematics 2026-05-12 Yesom Park , Eric Gelphman , Stanley Osher , Samy Wu Fung

This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks. Building on theoretical and practical advances in the field of Lipschitz neural…

Machine Learning · Statistics 2022-02-17 Alberto González-Sanz , Lucas de Lara , Louis Béthune , Jean-Michel Loubes

We propose a stable, parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs) under the constraint of a fixed computational budget. Differently from previous distributed GANs training techniques,…

Artificial Intelligence · Computer Science 2022-08-26 Massimiliano Lupo Pasini , Junqi Yin

In this paper, we investigate the training process of generative networks that use a type of probability density distance named particle-based distance as the objective function, e.g. MMD GAN, Cram\'er GAN, EIEG GAN. However, these GANs…

Machine Learning · Computer Science 2023-07-10 Chuqi Chen , Yue Wu , Yang Xiang

A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation.…

Machine Learning · Computer Science 2020-11-25 Alexia Jolicoeur-Martineau , Ioannis Mitliagkas

Generative-adversarial networks (GANs) have been used to produce data closely resembling example data in a compressed, latent space that is close to sufficient for reconstruction in the original vector space. The Wasserstein metric has been…

Machine Learning · Statistics 2022-10-10 Oliver Serang

Lack of ground-truth MR images impedes the common supervised training of neural networks for image reconstruction. To cope with this challenge, this paper leverages unpaired adversarial training for reconstruction networks, where the inputs…

Image and Video Processing · Electrical Eng. & Systems 2021-05-14 Ke Lei , Morteza Mardani , John M. Pauly , Shreyas S. Vasanawala

Lipschitz continuity recently becomes popular in generative adversarial networks (GANs). It was observed that the Lipschitz regularized discriminator leads to improved training stability and sample quality. The mainstream implementations of…

Machine Learning · Computer Science 2019-04-03 Zhiming Zhou , Jian Shen , Yuxuan Song , Weinan Zhang , Yong Yu

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparameters. One recent…

Machine Learning · Computer Science 2019-10-03 Thomas Pinetz , Daniel Soukup , Thomas Pock

This paper introduces a promising alternative method for training Generative Adversarial Networks (GANs) on large-scale datasets with clear theoretical guarantees. GANs are typically learned through a minimax game between a generator and a…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Chang Wan , Ke Fan , Xinwei Sun , Yanwei Fu , Minglu Li , Yunliang Jiang , Zhonglong Zheng

The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical properties of the generated distributions, we provide a…

Machine Learning · Statistics 2023-10-06 Arthur Stéphanovitch , Ugo Tanielian , Benoît Cadre , Nicolas Klutchnikoff , Gérard Biau

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 Felix Juefei-Xu , Vishnu Naresh Boddeti , Marios Savvides