{"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/on-gans-and-gmms","title":"On GANs and GMMs","arxiv_id":"1805.12462","date":"2018-05-31","proceeding":"NeurIPS 2018 12","authors":["Eitan Richardson","Yair Weiss"],"abstract":"A longstanding problem in machine learning is to find unsupervised methods\nthat can learn the statistical structure of high dimensional signals. In recent\nyears, GANs have gained much attention as a possible solution to the problem,\nand in particular have shown the ability to generate remarkably realistic high\nresolution sampled images. At the same time, many authors have pointed out that\nGANs may fail to model the full distribution (\"mode collapse\") and that using\nthe learned models for anything other than generating samples may be very\ndifficult. In this paper, we examine the utility of GANs in learning\nstatistical models of images by comparing them to perhaps the simplest\nstatistical model, the Gaussian Mixture Model. First, we present a simple\nmethod to evaluate generative models based on relative proportions of samples\nthat fall into predetermined bins. Unlike previous automatic methods for\nevaluating models, our method does not rely on an additional neural network nor\ndoes it require approximating intractable computations. Second, we compare the\nperformance of GANs to GMMs trained on the same datasets. While GMMs have\npreviously been shown to be successful in modeling small patches of images, we\nshow how to train them on full sized images despite the high dimensionality.\nOur results show that GMMs can generate realistic samples (although less sharp\nthan those of GANs) but also capture the full distribution, which GANs fail to\ndo. Furthermore, GMMs allow efficient inference and explicit representation of\nthe underlying statistical structure. Finally, we discuss how GMMs can be used\nto generate sharp images.","url_abs":"http://arxiv.org/abs/1805.12462v2","url_pdf":"http://arxiv.org/pdf/1805.12462v2.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":"on-gans-and-gmms","repo_url":"https://github.com/eitanrich/gans-n-gmms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"on-gans-and-gmms","repo_url":"https://github.com/KonstantinPakulev/OnGansAndGMMs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"on-gans-and-gmms","repo_url":"https://github.com/eitanrich/torch-mfa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.12462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.12462"}},"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/eitanrich/torch-mfa","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eitanrich/gans-n-gmms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KonstantinPakulev/OnGansAndGMMs","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"435dc481ad3f794f","entry":"load_images","repo":"eitanrich/gans-n-gmms","repo_kind":"official","path":"ndb_mnist_demo.py","file_url":"https://github.com/eitanrich/gans-n-gmms/blob/HEAD/ndb_mnist_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"435dc481ad3f794f"}},{"code_sha256_prefix":"d47ee5d50b52acef","entry":"load_labels","repo":"eitanrich/gans-n-gmms","repo_kind":"official","path":"ndb_mnist_demo.py","file_url":"https://github.com/eitanrich/gans-n-gmms/blob/HEAD/ndb_mnist_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d47ee5d50b52acef"}},{"code_sha256_prefix":"d2edf142969e6c80","entry":"load_mnist_data","repo":"eitanrich/gans-n-gmms","repo_kind":"official","path":"ndb_mnist_demo.py","file_url":"https://github.com/eitanrich/gans-n-gmms/blob/HEAD/ndb_mnist_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2edf142969e6c80"}},{"code_sha256_prefix":"3817f03c02b35f03","entry":"sample_to_np_image","repo":"eitanrich/torch-mfa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/eitanrich/torch-mfa/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3817f03c02b35f03"}},{"code_sha256_prefix":"866a59985a96387b","entry":"samples_to_mosaic","repo":"eitanrich/torch-mfa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/eitanrich/torch-mfa/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"866a59985a96387b"}},{"code_sha256_prefix":"e2fb4ec2cb26e054","entry":"samples_to_np_images","repo":"eitanrich/torch-mfa","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/eitanrich/torch-mfa/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2fb4ec2cb26e054"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}