paper-with-me

Papers

Approximating Probability Distributions by using Wasserstein Generative Adversarial Networks

2021-03-18 · Yihang Gao, Michael K. Ng, Mingjie Zhou

Studied here are Wasserstein generative adversarial networks (WGANs) with GroupSort neural networks as their discriminators. It is shown that the error bound of the approximation for the target distribution depends on the width and depth (capacity) of the generators and discriminators and the number of samples in training. A quantified generalization bound is established for the Wasserstein distance between the generated and target distributions. According to the theoretical results, WGANs have a higher requirement for the capacity of discriminators than that of generators, which is consistent with some existing results. More importantly, the results with overly deep and wide (high-capacity) generators may be worse than those with low-capacity generators if discriminators are insufficiently strong. Numerical results obtained using Swiss roll and MNIST datasets confirm the theoretical results.

📄 PDF Abstract BibTeX arXiv:2103.10060

Code (0)

등록된 구현이 없습니다.

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

On the capacity of deep generative networks for approximating distributions

2021-01-29 · Yunfei Yang, Zhen Li, Yang Wang

We study the efficacy and efficiency of deep generative networks for approximating probability distributions. We prove that neural networks can transform a low-dimensional source distribution to a distribution that is ar…

Learning Distributions by Generative Adversarial Networks: Approximation and Generalization

2022-05-25 · Yunfei Yang

We study how well generative adversarial networks (GAN) learn probability distributions from finite samples by analyzing the convergence rates of these models. Our analysis is based on a new oracle inequality that decomp…

Generalization BoundsLearning Theory

Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport

2024-02-08 · Jaemoo Choi, Jaewoong Choi, Myungjoo Kang

Wasserstein Gradient Flow (WGF) describes the gradient dynamics of probability density within the Wasserstein space. WGF provides a promising approach for conducting optimization over the probability distributions. Numer…

From GAN to WGAN

2019-04-18 · Lilian Weng

This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to improve GANs' training by adopting a smooth metric for measuring the dista…

Generative Adversarial NetworkMath

Ambiguity set and learning via Bregman and Wasserstein

2017-05-23 · Xin Guo, Johnny Hong, Nan Yang

Construction of ambiguity set in robust optimization relies on the choice of divergences between probability distributions. In distribution learning, choosing appropriate probability distributions based on observed data …

BIG-bench Machine Learning