On optimal solutions of classical and sliced Wasserstein GANs with non-Gaussian data

• URL: http://arxiv.org/abs/2509.06505v1
• Date: Mon, 08 Sep 2025 10:10:37 GMT
• Title: On optimal solutions of classical and sliced Wasserstein GANs with non-Gaussian data
• Authors: Yu-Jui Huang, Hsin-Hua Shen, Yu-Chih Huang, Wan-Yi Lin, Shih-Chun Lin,
• Abstract summary: generative adversarial network (GAN) aims to approximate an unknown distribution via a parameterized neural network (NN)<n>One of the most promising GAN variants is the Wasserstein GAN (WGAN)<n>We derive closed-form optimal parameters for one-dimensional WGANs when the NN has non-linear activation functions and the data is non-Gaussian.
• Score: 10.09163122660547
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The generative adversarial network (GAN) aims to approximate an unknown distribution via a parameterized neural network (NN). While GANs have been widely applied in reinforcement and semisupervised learning as well as computer vision tasks, selecting their parameters often needs an exhaustive search and only a few selection methods can be proved to be theoretically optimal. One of the most promising GAN variants is the Wasserstein GAN (WGAN). Prior work on optimal parameters for WGAN is limited to the linear-quadratic-Gaussian (LQG) setting, where the NN is linear and the data is Gaussian. In this paper, we focus on the characterization of optimal WGAN parameters beyond the LQG setting. We derive closed-form optimal parameters for one-dimensional WGANs when the NN has non-linear activation functions and the data is non-Gaussian. To extend this to high-dimensional WGANs, we adopt the sliced Wasserstein framework and replace the constraint on marginal distributions of the randomly projected data by a constraint on the joint distribution of the original (unprojected) data. We show that the linear generator can be asymptotically optimal for sliced WGAN with non-Gaussian data. Empirical studies show that our closed-form WGAN parameters have good convergence behavior with data under both Gaussian and Laplace distributions. Also, compared to the r principal component analysis (r-PCA) solution, our proposed solution for sliced WGAN can achieve the same performance while requiring less computational resources.

Related papers

• Optimal Transportation and Alignment Between Gaussian Measures [80.4634530260329]
  Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for datasets.<n>Because these frameworks are computationally expensive, large-scale applications often rely on closed-form solutions for Gaussian distributions under quadratic cost.<n>This work provides a comprehensive treatment of Gaussian, quadratic cost OT and inner product GW (IGW) alignment, closing several gaps in the literature to broaden applicability.
  arXiv  Detail & Related papers  (2025-12-03T09:01:48Z)
• On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension [32.98264375121064]
  We derive statistical guarantees on the estimated densities in terms of the intrinsic dimension of the data and the latent space.<n>We demonstrate that GANs can effectively achieve the minimax optimal rate even for non-smooth underlying distributions.
  arXiv  Detail & Related papers  (2024-01-28T23:18:10Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Generative Adversarial Neural Operators [59.21759531471597]
  We propose the generative adversarial neural operator (GANO), a generative model paradigm for learning probabilities on infinite-dimensional function spaces. GANO consists of two main components, a generator neural operator and a discriminator neural functional. We empirically study GANOs in controlled cases where both input and output functions are samples from GRFs and compare its performance to the finite-dimensional counterpart GAN.
  arXiv  Detail & Related papers  (2022-05-06T05:12:22Z)
• Robust Estimation for Nonparametric Families via Generative Adversarial Networks [92.64483100338724]
  We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems. Our work extend these to robust mean estimation, second moment estimation, and robust linear regression. In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
  arXiv  Detail & Related papers  (2022-02-02T20:11:33Z)
• Optimal 1-Wasserstein Distance for WGANs [2.1174215880331775]
  We provide a thorough analysis of Wasserstein GANs (WGANs) in both the finite sample and regimes. We derive in passing new results on optimal transport theory in the semi-discrete setting.
  arXiv  Detail & Related papers  (2022-01-08T13:04:03Z)
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions [31.952858521063277]
  We analyze the impact of Wasserstein GANs with two-layer neural network discriminators through the lens of convex duality. We further demonstrate the power of different activation functions of discriminator.
  arXiv  Detail & Related papers  (2021-07-12T18:33:49Z)
• Understanding Overparameterization in Generative Adversarial Networks [56.57403335510056]
  Generative Adversarial Networks (GANs) are used to train non- concave mini-max optimization problems. A theory has shown the importance of the gradient descent (GD) to globally optimal solutions. We show that in an overized GAN with a $1$-layer neural network generator and a linear discriminator, the GDA converges to a global saddle point of the underlying non- concave min-max problem.
  arXiv  Detail & Related papers  (2021-04-12T16:23:37Z)
• Monte Carlo Simulation of SDEs using GANs [0.0]
  We investigate if GANs can also be used to approximate one-dimensional geometric Ito differential equations (SDEs) Standard GANs are only able to approximate processes in distribution, yielding a weak approximation to the SDE. A conditional GAN architecture is proposed that enables strong approximation. We compare the input-output map obtained with the standard GAN and supervised GAN and show experimentally that the standard GAN may fail to provide a path-wise approximation.
  arXiv  Detail & Related papers  (2021-04-03T16:06:30Z)
• Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
  We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN) Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one. We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
  arXiv  Detail & Related papers  (2020-08-19T12:35:55Z)
• Towards GANs' Approximation Ability [8.471366736328811]
  This paper will first theoretically analyze GANs' approximation property. We prove that the generator with the input latent variable in GANs can universally approximate the potential data distribution. In the practical dataset, four GANs using SDG can also outperform the corresponding traditional GANs when the model architectures are smaller.
  arXiv  Detail & Related papers  (2020-04-10T02:40:16Z)
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator [85.68825725223873]
  Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. We introduce the Discriminator Contrastive Divergence, which is well motivated by the property of WGAN's discriminator. We demonstrate the benefits of significant improved generation on both synthetic data and several real-world image generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-05T01:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.