# Quantitatively Evaluating GANs With Divergences Proposed for Training

arXiv: https://arxiv.org/abs/1803.01045 · HTML: https://mlsanity.com/paper/1803.01045/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2018.

## Built on by (most cited first, 4 of 4)

- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals](https://mlsanity.com/paper/2106.07898/) (2021)
- [PolyGraph Discrepancy: a classifier-based metric for graph generation](https://mlsanity.com/paper/2510.06122/) (2025)
- [Are conditional GANs explicitly conditional?](https://mlsanity.com/paper/2106.15011/) (2021)

## Abstract (arXiv)

Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application. However, we currently lack quantitative methods for model assessment. Because of this, while many GAN variants are being proposed, we have relatively little understanding of their relative abilities. In this paper, we evaluate the performance of various types of GANs using divergence and distance functions typically used only for training. We observe consistency across the various proposed metrics and, interestingly, the test-time metrics do not favour networks that use the same training-time criterion. We also compare the proposed metrics to human perceptual scores.