{"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/learning-implicit-generative-models-with-the","title":"Learning Implicit Generative Models with the Method of Learned Moments","arxiv_id":"1806.11006","date":"2018-06-28","proceeding":"ICML 2018 7","authors":["Suman Ravuri","Shakir Mohamed","Mihaela Rosca","Oriol Vinyals"],"abstract":"We propose a method of moments (MoM) algorithm for training large-scale\nimplicit generative models. Moment estimation in this setting encounters two\nproblems: it is often difficult to define the millions of moments needed to\nlearn the model parameters, and it is hard to determine which properties are\nuseful when specifying moments. To address the first issue, we introduce a\nmoment network, and define the moments as the network's hidden units and the\ngradient of the network's output with the respect to its parameters. To tackle\nthe second problem, we use asymptotic theory to highlight desiderata for\nmoments -- namely they should minimize the asymptotic variance of estimated\nmodel parameters -- and introduce an objective to learn better moments. The\nsequence of objectives created by this Method of Learned Moments (MoLM) can\ntrain high-quality neural image samplers. On CIFAR-10, we demonstrate that\nMoLM-trained generators achieve significantly higher Inception Scores and lower\nFrechet Inception Distances than those trained with gradient\npenalty-regularized and spectrally-normalized adversarial objectives. These\ngenerators also achieve nearly perfect Multi-Scale Structural Similarity Scores\non CelebA, and can create high-quality samples of 128x128 images.","url_abs":"http://arxiv.org/abs/1806.11006v1","url_pdf":"http://arxiv.org/pdf/1806.11006v1.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":"learning-implicit-generative-models-with-the","repo_url":"https://github.com/cibeah/molm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.11006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.11006"}},"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/cibeah/molm","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"48afd1f1fd9b238b","entry":"generate","repo":"cibeah/molm","repo_kind":"listed","path":"src/generate.py","file_url":"https://github.com/cibeah/molm/blob/HEAD/src/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48afd1f1fd9b238b"}},{"code_sha256_prefix":"3f4ce6e40040746a","entry":"sample_true","repo":"cibeah/molm","repo_kind":"listed","path":"src/generate.py","file_url":"https://github.com/cibeah/molm/blob/HEAD/src/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f4ce6e40040746a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}