{"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/gilbo-one-metric-to-measure-them-all","title":"GILBO: One Metric to Measure Them All","arxiv_id":"1802.04874","date":"2018-02-13","proceeding":"NeurIPS 2018 12","authors":["Alexander A. Alemi","Ian Fischer"],"abstract":"We propose a simple, tractable lower bound on the mutual information\ncontained in the joint generative density of any latent variable generative\nmodel: the GILBO (Generative Information Lower BOund). It offers a\ndata-independent measure of the complexity of the learned latent variable\ndescription, giving the log of the effective description length. It is\nwell-defined for both VAEs and GANs. We compute the GILBO for 800 GANs and VAEs\neach trained on four datasets (MNIST, FashionMNIST, CIFAR-10 and CelebA) and\ndiscuss the results.","url_abs":"http://arxiv.org/abs/1802.04874v3","url_pdf":"http://arxiv.org/pdf/1802.04874v3.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":"gilbo-one-metric-to-measure-them-all","repo_url":"https://github.com/google/compare_gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04874","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}