{"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/analysis-of-learning-a-flow-based-generative","title":"Analysis of learning a flow-based generative model from limited sample complexity","arxiv_id":"2310.03575","date":"2023-10-05","proceeding":null,"authors":["Hugo Cui","Florent Krzakala","Eric Vanden-Eijnden","Lenka Zdeborová"],"abstract":"We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-to-end analysis of the problem. First, we provide a tight closed-form characterization of the learnt velocity field, when parametrized by a shallow denoising auto-encoder trained on a finite number $n$ of samples from the target distribution. Building on this analysis, we provide a sharp description of the corresponding generative flow, which pushes the base Gaussian density forward to an approximation of the target density. In particular, we provide closed-form formulae for the distance between the mean of the generated mixture and the mean of the target mixture, which we show decays as $\\Theta_n(\\frac{1}{n})$. Finally, this rate is shown to be in fact Bayes-optimal.","url_abs":"https://arxiv.org/abs/2310.03575v2","url_pdf":"https://arxiv.org/pdf/2310.03575v2.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":"analysis-of-learning-a-flow-based-generative","repo_url":"https://github.com/spoc-group/diffusion_gmm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"form","task_name":"Form"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.03575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03575"}},"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/spoc-group/diffusion_gmm","reach":null}],"summary":{"ran_violates":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"7863a09ad2e76bd3","entry":"alpha","repo":"spoc-group/diffusion_gmm","repo_kind":"official","path":"Simulations.py","file_url":"https://github.com/spoc-group/diffusion_gmm/blob/HEAD/Simulations.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7863a09ad2e76bd3"}},{"code_sha256_prefix":"140599efaa101c71","entry":"beta","repo":"spoc-group/diffusion_gmm","repo_kind":"official","path":"Simulations.py","file_url":"https://github.com/spoc-group/diffusion_gmm/blob/HEAD/Simulations.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"140599efaa101c71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}