# How Well Can Generative Adversarial Networks Learn Densities: A Nonparametric View

arXiv: https://arxiv.org/abs/1712.08244 · HTML: https://mlsanity.com/paper/1712.08244/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2017.

## Built on by (most cited first, 14 of 14)

- [Diffusion Models are Minimax Optimal Distribution Estimators](https://mlsanity.com/paper/2303.01861/) (2023)
- [From optimal score matching to optimal sampling](https://mlsanity.com/paper/2409.07032/) (2024)
- [On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds](https://mlsanity.com/paper/2302.13183/) (2023)
- [Dimension-independent rates for structured neural density estimation](https://mlsanity.com/paper/2411.15095/) (2024)
- [Dissecting adaptive methods in GANs](https://mlsanity.com/paper/2210.04319/) (2022)
- [A Wasserstein perspective of Vanilla GANs](https://mlsanity.com/paper/2403.15312/) (2024)
- [Breaking the curse of dimensionality in structured density estimation](https://mlsanity.com/paper/2410.07685/) (2024)
- [Bounds on Lp errors in density ratio estimation via f-divergence loss functions](https://mlsanity.com/paper/2410.01516/) (2024)
- [A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers](https://mlsanity.com/paper/2502.01310/) (2025)
- [Theoretical Insights into CycleGAN: Analyzing Approximation and Estimation Errors in Unpaired Data Generation](https://mlsanity.com/paper/2407.11678/) (2024)
- [Scalable Sobolev IPM for Probability Measures on a Graph](https://mlsanity.com/paper/2502.00737/) (2025)
- [Generalized Sobolev IPM for Graph-Based Measures](https://mlsanity.com/paper/2510.25591/) (2025)
- [Theoretical Analysis of Measure Consistency Regularization for Partially Observed Data](https://mlsanity.com/paper/2602.01437/) (2026)
- [Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training](https://mlsanity.com/paper/2602.16065/) (2026)

## Abstract (arXiv)

We study in this paper the rate of convergence for learning densities under the Generative Adversarial Networks (GAN) framework, borrowing insights from nonparametric statistics. We introduce an improved GAN estimator that achieves a faster rate, through simultaneously leveraging the level of smoothness in the target density and the evaluation metric, which in theory remedies the mode collapse problem reported in the literature. A minimax lower bound is constructed to show that when the dimension is large, the exponent in the rate for the new GAN estimator is near optimal. One can view our results as answering in a quantitative way how well GAN learns a wide range of densities with different smoothness properties, under a hierarchy of evaluation metrics. As a byproduct, we also obtain improved generalization bounds for GAN with deeper ReLU discriminator network.