{"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/can-push-forward-generative-models-fit","title":"Can Push-forward Generative Models Fit Multimodal Distributions?","arxiv_id":"2206.14476","date":"2022-06-29","proceeding":null,"authors":["Antoine Salmona","Valentin De Bortoli","Julie Delon","Agnès Desolneux"],"abstract":"Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we call them \"push-forward\" models and study their expressivity. We show that the Lipschitz constant of these generative networks has to be large in order to fit multimodal distributions. More precisely, we show that the total variation distance and the Kullback-Leibler divergence between the generated and the data distribution are bounded from below by a constant depending on the mode separation and the Lipschitz constant. Since constraining the Lipschitz constants of neural networks is a common way to stabilize generative models, there is a provable trade-off between the ability of push-forward models to approximate multimodal distributions and the stability of their training. We validate our findings on one-dimensional and image datasets and empirically show that generative models consisting of stacked networks with stochastic input at each step, such as diffusion models do not suffer of such limitations.","url_abs":"https://arxiv.org/abs/2206.14476v2","url_pdf":"https://arxiv.org/pdf/2206.14476v2.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":"can-push-forward-generative-models-fit","repo_url":"https://github.com/antoinesalmona/push-forward-generative-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.14476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.14476"}},"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/antoinesalmona/push-forward-generative-models","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"official":{"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":6,"samples":[{"code_sha256_prefix":"97344ffa10736334","entry":"gen_model","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_dim1.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_dim1.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":"97344ffa10736334"}},{"code_sha256_prefix":"6d4e547b05941182","entry":"histo_projection","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_GM_MNIST.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_GM_MNIST.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":"6d4e547b05941182"}},{"code_sha256_prefix":"15ba4e666f646be3","entry":"train_model","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_dim1.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_dim1.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":"15ba4e666f646be3"}},{"code_sha256_prefix":"0b153cc7c2879d2a","entry":"train_model","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_GM_MNIST.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_GM_MNIST.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":"0b153cc7c2879d2a"}},{"code_sha256_prefix":"9f1690191597e113","entry":"train_model","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_subset_MNIST.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_subset_MNIST.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":"9f1690191597e113"}},{"code_sha256_prefix":"f384d1e7ae6f3901","entry":"wasserstein_projection","repo":"antoinesalmona/push-forward-generative-models","repo_kind":"official","path":"runner_subset_MNIST.py","file_url":"https://github.com/antoinesalmona/push-forward-generative-models/blob/HEAD/runner_subset_MNIST.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":"f384d1e7ae6f3901"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}