{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/evaluating-generative-adversarial-networks-on","title":"Evaluating Generative Adversarial Networks on Explicitly Parameterized Distributions","arxiv_id":"1812.10782","date":"2018-12-27","proceeding":null,"authors":["Shayne O'Brien","Matt Groh","Abhimanyu Dubey"],"abstract":"The true distribution parameterizations of commonly used image datasets are\ninaccessible. Rather than designing metrics for feature spaces with unknown\ncharacteristics, we propose to measure GAN performance by evaluating on\nexplicitly parameterized, synthetic data distributions. As a case study, we\nexamine the performance of 16 GAN variants on six multivariate distributions of\nvarying dimensionalities and training set sizes. In this learning environment,\nwe observe that: GANs exhibit similar performance trends across\ndimensionalities; learning depends on the underlying distribution and its\ncomplexity; the number of training samples can have a large impact on\nperformance; evaluation and relative comparisons are metric-dependent; diverse\nsets of hyperparameters can produce a \"best\" result; and some GANs are more\nrobust to hyperparameter changes than others. These observations both\ncorroborate findings of previous GAN evaluation studies and make novel\ncontributions regarding the relationship between size, complexity, and GAN\nperformance.","url_abs":"http://arxiv.org/abs/1812.10782v1","url_pdf":"http://arxiv.org/pdf/1812.10782v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"evaluating-generative-adversarial-networks-on","repo_url":"https://github.com/shayneobrien/explicit-gan-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}