paper-with-me

홈 › Papers

Banach Wasserstein GAN

2018-06-18 · NeurIPS 2018 12 · Jonas Adler, Sebastian Lunz

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 induces a notion of distance between probability distributions of images. So far the community has considered $\ell^2$ as the underlying distance. We generalize the theory of WGAN with gradient penalty to Banach spaces, allowing practitioners to select the features to emphasize in the generator. We further discuss the effect of some particular choices of underlying norms, focusing on Sobolev norms. Finally, we demonstrate a boost in performance for an appropriate choice of norm on CIFAR-10 and CelebA.

📄 PDF Abstract BibTeX arXiv:1806.06621

Code (2)

adler-j/bwgan 공식 구현 tf
new-okaerinasai/bwgan_pytorch pytorch

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…
WGAN Wasserstein GAN, or WGAN, is a type of generative adversarial network that minimizes an approximation of the Earth-Mover's distance (EM) rather than the Jensen-Shannon…

Similar Papers 제목 키워드 기반

Sharp bounds for max-sliced Wasserstein distances

2024-03-01 · March T. Boedihardjo

We obtain essentially matching upper and lower bounds for the expected max-sliced 1-Wasserstein distance between a probability measure on a separable Hilbert space and its empirical distribution from $n$ samples. By prov…

Slicing Wasserstein Over Wasserstein Via Functional Optimal Transport

2025-09-26 · Moritz Piening, Robert Beinert arxiv

Wasserstein distances define a metric between probability measures on arbitrary metric spaces, including meta-measures (measures over measures). The resulting Wasserstein over Wasserstein (WoW) distance is a powerful, bu…

Gaussian Processes

Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning

2026-04-06 · Andrew Qing He arxiv

Computing pairwise Wasserstein distances is a fundamental bottleneck in data analysis pipelines. Motivated by the classical Kuratowski embedding theorem, we propose two neural architectures for learning to approximate th…

Metric Learning

An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning

2023-04-24 · Anastasis Kratsios, Chong Liu, Matti Lassas, Maarten V. de Hoop 외

Motivated by the developing mathematics of deep learning, we build universal functions approximators of continuous maps between arbitrary Polish metric spaces $\mathcal{X}$ and $\mathcal{Y}$ using elementary functions be…

Algebraic function based Banach space valued ordinary and fractional neural network approximations

2022-02-11 · George A Anastassiou

Here we research the univariate quantitative approximation, ordinary and fractional, of Banach space valued continuous functions on a compact interval or all the real line by quasi-interpolation Banach space valued neura…