{"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/adversarial-variational-bayes-unifying","title":"Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks","arxiv_id":"1701.04722","date":"2017-01-17","proceeding":"ICML 2017 8","authors":["Lars Mescheder","Sebastian Nowozin","Andreas Geiger"],"abstract":"Variational Autoencoders (VAEs) are expressive latent variable models that\ncan be used to learn complex probability distributions from training data.\nHowever, the quality of the resulting model crucially relies on the\nexpressiveness of the inference model. We introduce Adversarial Variational\nBayes (AVB), a technique for training Variational Autoencoders with arbitrarily\nexpressive inference models. We achieve this by introducing an auxiliary\ndiscriminative network that allows to rephrase the maximum-likelihood-problem\nas a two-player game, hence establishing a principled connection between VAEs\nand Generative Adversarial Networks (GANs). We show that in the nonparametric\nlimit our method yields an exact maximum-likelihood assignment for the\nparameters of the generative model, as well as the exact posterior distribution\nover the latent variables given an observation. Contrary to competing\napproaches which combine VAEs with GANs, our approach has a clear theoretical\njustification, retains most advantages of standard Variational Autoencoders and\nis easy to implement.","url_abs":"http://arxiv.org/abs/1701.04722v4","url_pdf":"http://arxiv.org/pdf/1701.04722v4.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":"adversarial-variational-bayes-unifying","repo_url":"https://github.com/LMescheder/AdversarialVariationalBayes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.04722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.04722"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LMescheder/AdversarialVariationalBayes","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6ba526403646bcdf","entry":"get_bbox","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/utils.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba526403646bcdf"}},{"code_sha256_prefix":"de3420581345df2c","entry":"get_image","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/utils.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de3420581345df2c"}},{"code_sha256_prefix":"241589a9c025efb6","entry":"get_inputs","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/inputs.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/inputs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"241589a9c025efb6"}},{"code_sha256_prefix":"733565c80939c68e","entry":"get_inputs_image","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/inputs.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/inputs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"733565c80939c68e"}},{"code_sha256_prefix":"be9ba2cafc92da04","entry":"get_inputs_mnist","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/inputs.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/inputs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be9ba2cafc92da04"}},{"code_sha256_prefix":"9efe599ca7ebe77a","entry":"save_images","repo":"LMescheder/AdversarialVariationalBayes","repo_kind":"listed","path":"avb/utils.py","file_url":"https://github.com/LMescheder/AdversarialVariationalBayes/blob/HEAD/avb/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9efe599ca7ebe77a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}