Sobolev GAN

2017-11-14 · ICLR 2018 1 · Youssef Mroueh, Chun-Liang Li, Tom Sercu, Anant Raj, Yu Cheng

We propose a new Integral Probability Metric (IPM) between distributions: the Sobolev IPM. The Sobolev IPM compares the mean discrepancy of two distributions for functions (critic) restricted to a Sobolev ball defined with respect to a dominant measure $\mu$. We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis. The Dominant measure $\mu$ plays a crucial role as it defines the support on which conditional CDFs are compared. Sobolev IPM can be seen as an extension of the one dimensional Von-Mises Cram\'er statistics to high dimensional distributions. We show how Sobolev IPM can be used to train Generative Adversarial Networks (GANs). We then exploit the intrinsic conditioning implied by Sobolev IPM in text generation. Finally we show that a variant of Sobolev GAN achieves competitive results in semi-supervised learning on CIFAR-10, thanks to the smoothness enforced on the critic by Sobolev GAN which relates to Laplacian regularization.

📄 PDF Abstract BibTeX arXiv:1711.04894

Code (2)

chanshing/sobolev_gan pytorch

zzmtsvv/adversarial pytorch

Tasks

Text Generation

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

MSINO: Curvature-Aware Sobolev Optimization for Manifold Neural Networks

2026-02-26 · Suresan Pareth arxiv

We introduce Manifold Sobolev Informed Neural Optimization (MSINO), a curvature aware training framework for neural networks defined on Riemannian manifolds. The method replaces standard Euclidean derivative supervision …

Generalized Sobolev IPM for Graph-Based Measures

2025-10-29 · Tam Le, Truyen Nguyen, Hideitsu Hino, Kenji Fukumizu arxiv

We study the Sobolev IPM problem for measures supported on a graph metric space, where critic function is constrained to lie within the unit ball defined by Sobolev norm. While Le et al. (2025) achieved scalable computat…

Computational Efficiency Document Classification

Particle methods enable fast and simple approximation of Sobolev gradients in image segmentation

2014-03-02 · Ivo F. Sbalzarini, Sophie Schneider, Janick Cardinale

Bio-image analysis is challenging due to inhomogeneous intensity distributions and high levels of noise in the images. Bayesian inference provides a principled way for regularizing the problem using prior knowledge. A fu…

Bayesian Inference Image Segmentation Segmentation Semantic Segmentation

Approximations with deep neural networks in Sobolev time-space

2020-12-23 · Ahmed Abdeljawad, Philipp Grohs

Solutions of evolution equation generally lies in certain Bochner-Sobolev spaces, in which the solution may has regularity and integrability properties for the time variable that can be different for the space variables.…

Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

2026-06-16 · Yahong Yang, Zecheng Zhang, Wei Zhu, Wenjing Liao 외 arxiv

We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input functi…