{"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/training-energy-based-normalizing-flow-with-1","title":"Training Energy-Based Normalizing Flow with Score-Matching Objectives","arxiv_id":"2305.15267","date":"2023-05-24","proceeding":"NeurIPS 2023 11","authors":["Chen-Hao Chao","Wei-Fang Sun","Yen-Chang Hsu","Zsolt Kira","Chun-Yi Lee"],"abstract":"In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow). We demonstrate that by optimizing EBFlow with score-matching objectives, the computation of Jacobian determinants for linear transformations can be entirely bypassed. This feature enables the use of arbitrary linear layers in the construction of flow-based models without increasing the computational time complexity of each training iteration from $O(D^2L)$ to $O(D^3L)$ for an $L$-layered model that accepts $D$-dimensional inputs. This makes the training of EBFlow more efficient than the commonly-adopted maximum likelihood training method. In addition to the reduction in runtime, we enhance the training stability and empirical performance of EBFlow through a number of techniques developed based on our analysis of the score-matching methods. The experimental results demonstrate that our approach achieves a significant speedup compared to maximum likelihood estimation while outperforming prior methods with a noticeable margin in terms of negative log-likelihood (NLL).","url_abs":"https://arxiv.org/abs/2305.15267v2","url_pdf":"https://arxiv.org/pdf/2305.15267v2.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":"training-energy-based-normalizing-flow-with-1","repo_url":"https://github.com/chen-hao-chao/ebflow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.15267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15267"}},"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/chen-hao-chao/ebflow","reach":null}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"e40e8a4a47c88730","entry":"Conv2dZero","repo":"chen-hao-chao/ebflow","repo_kind":"official","path":"real_world/ebflow/layers/coupling.py","file_url":"https://github.com/chen-hao-chao/ebflow/blob/HEAD/real_world/ebflow/layers/coupling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e40e8a4a47c88730"}},{"code_sha256_prefix":"237f2a7dbcf50139","entry":"Coupling","repo":"chen-hao-chao/ebflow","repo_kind":"official","path":"real_world/ebflow/layers/coupling.py","file_url":"https://github.com/chen-hao-chao/ebflow/blob/HEAD/real_world/ebflow/layers/coupling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"237f2a7dbcf50139"}},{"code_sha256_prefix":"a20f619e2668bebb","entry":"Swish","repo":"chen-hao-chao/ebflow","repo_kind":"official","path":"real_world/ebflow/layers/coupling.py","file_url":"https://github.com/chen-hao-chao/ebflow/blob/HEAD/real_world/ebflow/layers/coupling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a20f619e2668bebb"}},{"code_sha256_prefix":"2b321af83cfae317","entry":"FlowLayer","repo":"chen-hao-chao/ebflow","repo_kind":"official","path":"real_world/ebflow/layers/coupling.py","file_url":"https://github.com/chen-hao-chao/ebflow/blob/HEAD/real_world/ebflow/layers/coupling.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":"2b321af83cfae317"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}