中文
相关论文

相关论文: MonoFlow: Rethinking Divergence GANs via the Persp…

200 篇论文

Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require solving a minmax optimization problem to global optimality,…

机器学习 · 计算机科学 2020-07-03 Qi Lei , Jason D. Lee , Alexandros G. Dimakis , Constantinos Daskalakis

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…

机器学习 · 计算机科学 2023-07-10 Chuqi Chen , Yue Wu , Yang Xiang

Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. However, it has been noted that maximizing the log-likelihood within an energy-based…

机器学习 · 计算机科学 2023-10-03 Omri Ben-Dov , Pravir Singh Gupta , Victoria Abrevaya , Michael J. Black , Partha Ghosh

This paper proposes a new theoretical lens to view Wasserstein generative adversarial networks (WGANs). To minimize the Wasserstein-1 distance between the true data distribution and our estimate of it, we derive a distribution-dependent…

机器学习 · 统计学 2025-02-05 Zachariah Malik , Yu-Jui Huang

Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updates. We introduce W-Flow, a framework for training a…

机器学习 · 计算机科学 2026-05-28 Jiaqi Han , Puheng Li , Qiushan Guo , Renyuan Xu , Stefano Ermon , Emmanuel J. Candès

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…

计算机视觉与模式识别 · 计算机科学 2017-04-18 Felix Juefei-Xu , Vishnu Naresh Boddeti , Marios Savvides

Generative adversarial networks (GANs) are a family of generative models that do not minimize a single training criterion. Unlike other generative models, the data distribution is learned via a game between a generator (the generative…

We propose a novel modular inference approach combining two different generative models -- generative adversarial networks (GAN) and normalizing flows -- to approximate the posterior distribution of physics-based Bayesian inverse problems…

计算工程、金融与科学 · 计算机科学 2023-10-10 Agnimitra Dasgupta , Dhruv V Patel , Deep Ray , Erik A Johnson , Assad A Oberai

Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models…

机器学习 · 计算机科学 2018-01-08 Aditya Grover , Manik Dhar , Stefano Ermon

We propose a gradient flow procedure for generative modeling by transporting particles from an initial source distribution to a target distribution, where the gradient field on the particles is given by a noise-adaptive Wasserstein Gradient…

机器学习 · 计算机科学 2024-05-14 Alexandre Galashov , Valentin de Bortoli , Arthur Gretton

Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions using differential…

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the…

机器学习 · 计算机科学 2020-04-29 Shufei Zhang , Zhuang Qian , Kaizhu Huang , Jimin Xiao , Yuan He

Generative adversarial networks (GANs) are a machine learning framework comprising a generative model for sampling from a target distribution and a discriminative model for evaluating the proximity of a sample to the target distribution.…

量子物理 · 物理学 2021-07-22 Daniel Herr , Benjamin Obert , Matthias Rosenkranz

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…

机器学习 · 计算机科学 2019-10-03 Thomas Pinetz , Daniel Soukup , Thomas Pock

Generative Adversarial Networks (GANs) have been successful in producing outstanding results in areas as diverse as image, video, and text generation. Building on these successes, a large number of empirical studies have validated the…

机器学习 · 计算机科学 2021-06-21 Gérard Biau , Maxime Sangnier , Ugo Tanielian

Generative Adversarial Networks (GANs) have been impactful on many problems and applications but suffer from unstable training. The Wasserstein GAN (WGAN) leverages the Wasserstein distance to avoid the caveats in the minmax two-player…

机器学习 · 统计学 2021-09-14 Yao Chen , Qingyi Gao , Xiao Wang

Generative adversarial network (GAN) is a minimax game between a generator mimicking the true model and a discriminator distinguishing the samples produced by the generator from the real training samples. Given an unconstrained…

机器学习 · 计算机科学 2018-10-30 Farzan Farnia , David Tse

Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train.…

机器学习 · 计算机科学 2017-05-09 Zhimin Chen , Yuguang Tong

Training generative adversarial networks is unstable in high-dimensions as the true data distribution tends to be concentrated in a small fraction of the ambient space. The discriminator is then quickly able to classify nearly all generated…

机器学习 · 计算机科学 2018-06-26 Behnam Neyshabur , Srinadh Bhojanapalli , Ayan Chakrabarti

Generative adversarial networks (GANs) and normalizing flows are both approaches to density estimation that use deep neural networks to transform samples from an uninformative prior distribution to an approximation of the data distribution.…

机器学习 · 计算机科学 2021-12-15 Tianci Liu , Jeffrey Regier
‹ 上一页 1 2 3 10 下一页 ›