{"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/sliced-iterative-generator","title":"Sliced Iterative Normalizing Flows","arxiv_id":"2007.00674","date":"2020-07-01","proceeding":"ICML Workshop INNF 2021 7","authors":["Biwei Dai","Uros Seljak"],"abstract":"We develop an iterative (greedy) deep learning (DL) algorithm which is able to transform an arbitrary probability distribution function (PDF) into the target PDF. The model is based on iterative Optimal Transport of a series of 1D slices, matching on each slice the marginal PDF to the target. The axes of the orthogonal slices are chosen to maximize the PDF difference using Wasserstein distance at each iteration, which enables the algorithm to scale well to high dimensions. As special cases of this algorithm, we introduce two sliced iterative Normalizing Flow (SINF) models, which map from the data to the latent space (GIS) and vice versa (SIG). We show that SIG is able to generate high quality samples of image datasets, which match the GAN benchmarks, while GIS obtains competitive results on density estimation tasks compared to the density trained NFs, and is more stable, faster, and achieves higher $p(x)$ when trained on small training sets. SINF approach deviates significantly from the current DL paradigm, as it is greedy and does not use concepts such as mini-batching, stochastic gradient descent and gradient back-propagation through deep layers.","url_abs":"https://arxiv.org/abs/2007.00674v3","url_pdf":"https://arxiv.org/pdf/2007.00674v3.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":"sliced-iterative-generator","repo_url":"https://github.com/biweidai/SIG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sliced-iterative-generator","repo_url":"https://github.com/biweidai/SINF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"},{"method_slug":"sig","method_name":"SIG"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-fashion-mnist","task":"Image Generation","dataset":"Fashion-MNIST","model":"Sliced Iterative Generator","rank_in_archive_order":2,"of":7,"metrics":{"FID":"13.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-mnist","task":"Image Generation","dataset":"MNIST","model":"Sliced Iterative Generator","rank_in_archive_order":6,"of":15,"metrics":{"FID":"4.5","bits/dimension":"1.34"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.00674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00674"}},"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/biweidai/SIG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/biweidai/SINF","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"317038bbf1e9dea6","entry":"toimage","repo":"biweidai/SINF","repo_kind":"listed","path":"sinf/SIG.py","file_url":"https://github.com/biweidai/SINF/blob/HEAD/sinf/SIG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"317038bbf1e9dea6"}},{"code_sha256_prefix":"79dc956417fc1b4c","entry":"GIS","repo":"biweidai/SINF","repo_kind":"listed","path":"sinf/GIS.py","file_url":"https://github.com/biweidai/SINF/blob/HEAD/sinf/GIS.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":"79dc956417fc1b4c"}},{"code_sha256_prefix":"d0297731c19c4d45","entry":"add_one_layer_inverse","repo":"biweidai/SINF","repo_kind":"listed","path":"sinf/SIG.py","file_url":"https://github.com/biweidai/SINF/blob/HEAD/sinf/SIG.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":"d0297731c19c4d45"}},{"code_sha256_prefix":"e9d36e5bf9c963a2","entry":"preprocess","repo":"biweidai/SINF","repo_kind":"listed","path":"sinf/SIG.py","file_url":"https://github.com/biweidai/SINF/blob/HEAD/sinf/SIG.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":"e9d36e5bf9c963a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}