中文
相关论文

相关论文: The efficacy and generalizability of conditional G…

200 篇论文

The solution of probabilistic inverse problems for which the corresponding forward problem is constrained by physical principles is challenging. This is especially true if the dimension of the inferred vector is large and the prior…

机器学习 · 统计学 2023-06-09 Deep Ray , Javier Murgoitio-Esandi , Agnimitra Dasgupta , Assad A. Oberai

Inverse problems are ubiquitous in nature, arising in almost all areas of science and engineering ranging from geophysics and climate science to astrophysics and biomechanics. One of the central challenges in solving inverse problems is…

机器学习 · 统计学 2022-09-21 Dhruv V Patel , Deep Ray , Assad A Oberai

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

In this paper, we study a physics-informed algorithm for Wasserstein Generative Adversarial Networks (WGANs) for uncertainty quantification in solutions of partial differential equations. By using groupsort activation functions in…

数值分析 · 数学 2022-08-10 Yihang Gao , Michael K. Ng

Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for…

机器学习 · 统计学 2016-12-16 Theofanis Karaletsos

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution,…

计算机视觉与模式识别 · 计算机科学 2018-02-16 Antonia Creswell , Anil A Bharath

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

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

One of the main challenges in the parametrization of geological models is the ability to capture complex geological structures often observed in the subsurface. In recent years, generative adversarial networks (GAN) were proposed as an…

机器学习 · 统计学 2019-04-10 Shing Chan , Ahmed H. Elsheikh

The generative adversarial network (GAN) is a well-known model for learning high-dimensional distributions, but the mechanism for its generalization ability is not understood. In particular, GAN is vulnerable to the memorization phenomenon,…

机器学习 · 计算机科学 2026-02-18 Hongkang Yang , Weinan E

Solving inverse problems in scientific and engineering fields has long been intriguing and holds great potential for many applications, yet most techniques still struggle to address issues such as high dimensionality, nonlinearity and model…

机器学习 · 计算机科学 2024-05-24 Qiuyi Chen , Panagiotis Tsilifis , Mark Fuge

We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. The approach is based on Wasserstein information geometry. It defines a parametrization invariant…

机器学习 · 计算机科学 2021-02-16 Alex Tong Lin , Wuchen Li , Stanley Osher , Guido Montufar

Generative adversarial networks are a class of generative algorithms that have been widely used to produce state-of-the-art samples. In this paper, we investigate GAN to perform anomaly detection on time series dataset. In order to achieve…

机器学习 · 统计学 2018-12-12 Ilyass Haloui , Jayant Sen Gupta , Vincent Feuillard

The Bayesian inference approach is widely used to tackle inverse problems due to its versatile and natural ability to handle ill-posedness. However, it often faces challenges when dealing with situations involving continuous fields or…

数值分析 · 数学 2023-08-28 Xinchao Jiang , Xin Wang , Ziming Wen , Hu Wang

We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve in a unified manner forward, inverse and mixed stochastic problems based on a limited number of scattered measurements. Unlike standard GANs…

机器学习 · 统计学 2018-11-07 Liu Yang , Dongkun Zhang , George Em Karniadakis

Adversarial examples are a hot topic due to their abilities to fool a classifier's prediction. There are two strategies to create such examples, one uses the attacked classifier's gradients, while the other only requires access to the…

机器学习 · 计算机科学 2020-01-29 Jean-Christophe Burnel , Kilian Fatras , Nicolas Courty

The analysis of parametric and non-parametric uncertainties of very large dynamical systems requires the construction of a stochastic model of said system. Linear approaches relying on random matrix theory and principal componant analysis…

机器学习 · 统计学 2023-02-02 Hamza Boukraichi , Nissrine Akkari , Fabien Casenave , David Ryckelynck

Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. The Wasserstein metric used in WGANs is based on a notion of distance between individual images, which…

计算机视觉与模式识别 · 计算机科学 2019-01-14 Jonas Adler , Sebastian Lunz

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

We present a physics-informed Wasserstein GAN with gradient penalty (WGAN-GP) for solving the inverse Chafee--Infante problem on two-dimensional domains with Dirichlet boundary conditions. The objective is to reconstruct an unknown initial…

偏微分方程分析 · 数学 2026-01-13 Joseph L. Shomberg
‹ 上一页 1 2 3 10 下一页 ›