{"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/neural-autoregressive-flows","title":"Neural Autoregressive Flows","arxiv_id":"1804.00779","date":"2018-04-03","proceeding":"ICML 2018 7","authors":["Chin-wei Huang","David Krueger","Alexandre Lacoste","Aaron Courville"],"abstract":"Normalizing flows and autoregressive models have been successfully combined\nto produce state-of-the-art results in density estimation, via Masked\nAutoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based\nspeech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows\n(IAF). We unify and generalize these approaches, replacing the (conditionally)\naffine univariate transformations of MAF/IAF with a more general class of\ninvertible univariate transformations expressed as monotonic neural networks.\nWe demonstrate that the proposed neural autoregressive flows (NAF) are\nuniversal approximators for continuous probability distributions, and their\ngreater expressivity allows them to better capture multimodal target\ndistributions. Experimentally, NAF yields state-of-the-art performance on a\nsuite of density estimation tasks and outperforms IAF in variational\nautoencoders trained on binarized MNIST.","url_abs":"http://arxiv.org/abs/1804.00779v1","url_pdf":"http://arxiv.org/pdf/1804.00779v1.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":"neural-autoregressive-flows","repo_url":"https://github.com/CW-Huang/NAF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"neural-autoregressive-flows","repo_url":"https://github.com/RotemMayo/NAF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-autoregressive-flows","repo_url":"https://github.com/bossemel/NAF-Python3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"neural-autoregressive-flows","repo_url":"https://github.com/bradyneal/causal-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-autoregressive-flows","repo_url":"https://github.com/bradyneal/realcause","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-autoregressive-flows","repo_url":"https://github.com/francois-rozet/zuko","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00779"}},"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/CW-Huang/NAF","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bradyneal/realcause","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bradyneal/causal-benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/francois-rozet/zuko","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RotemMayo/NAF","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bossemel/NAF-Python3","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"repositories":2}},"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":"b8e95809ca2c17c9","entry":"sigmoid","repo":"bradyneal/realcause","repo_kind":"listed","path":"models/preprocess.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/models/preprocess.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8e95809ca2c17c9"}},{"code_sha256_prefix":"def2cd76c0341a40","entry":"args2fn","repo":"RotemMayo/NAF","repo_kind":"listed","path":"maf_experiments.py","file_url":"https://github.com/RotemMayo/NAF/blob/HEAD/maf_experiments.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":"def2cd76c0341a40"}},{"code_sha256_prefix":"a1027e5a50bc4a17","entry":"check_args","repo":"RotemMayo/NAF","repo_kind":"listed","path":"maf_experiments.py","file_url":"https://github.com/RotemMayo/NAF/blob/HEAD/maf_experiments.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":"a1027e5a50bc4a17"}},{"code_sha256_prefix":"2524fe91346c5d3d","entry":"cauchy","repo":"bradyneal/realcause","repo_kind":"listed","path":"models/preprocess.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/models/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2524fe91346c5d3d"}},{"code_sha256_prefix":"4c788dfaf976b644","entry":"extract_atom_clf_dataset","repo":"bradyneal/realcause","repo_kind":"listed","path":"models/gp.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/models/gp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c788dfaf976b644"}},{"code_sha256_prefix":"e8b6d8f84e1d4671","entry":"get_multivariate_results","repo":"bradyneal/realcause","repo_kind":"listed","path":"run_metrics.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/run_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8b6d8f84e1d4671"}},{"code_sha256_prefix":"8556e8eebe2354bb","entry":"get_univariate_results","repo":"bradyneal/realcause","repo_kind":"listed","path":"run_metrics.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/run_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8556e8eebe2354bb"}},{"code_sha256_prefix":"4560f0beb233e14c","entry":"logit","repo":"bradyneal/realcause","repo_kind":"listed","path":"models/preprocess.py","file_url":"https://github.com/bradyneal/realcause/blob/HEAD/models/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4560f0beb233e14c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}