{"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/flow-matching-for-scalable-simulation-based-1","title":"Flow Matching for Scalable Simulation-Based Inference","arxiv_id":"2305.17161","date":"2023-05-26","proceeding":"NeurIPS 2023 11","authors":["Maximilian Dax","Jonas Wildberger","Simon Buchholz","Stephen R. Green","Jakob H. Macke","Bernhard Schölkopf"],"abstract":"Neural posterior estimation methods based on discrete normalizing flows have become established tools for simulation-based inference (SBI), but scaling them to high-dimensional problems can be challenging. Building on recent advances in generative modeling, we here present flow matching posterior estimation (FMPE), a technique for SBI using continuous normalizing flows. Like diffusion models, and in contrast to discrete flows, flow matching allows for unconstrained architectures, providing enhanced flexibility for complex data modalities. Flow matching, therefore, enables exact density evaluation, fast training, and seamless scalability to large architectures--making it ideal for SBI. We show that FMPE achieves competitive performance on an established SBI benchmark, and then demonstrate its improved scalability on a challenging scientific problem: for gravitational-wave inference, FMPE outperforms methods based on comparable discrete flows, reducing training time by 30% with substantially improved accuracy. Our work underscores the potential of FMPE to enhance performance in challenging inference scenarios, thereby paving the way for more advanced applications to scientific problems.","url_abs":"https://arxiv.org/abs/2305.17161v2","url_pdf":"https://arxiv.org/pdf/2305.17161v2.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":"flow-matching-for-scalable-simulation-based-1","repo_url":"https://github.com/dingo-gw/flow-matching-posterior-estimation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17161"}},"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":"deterministic:regex_extraction","url":"https://github.com/dingo-gw/dingo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dingo-gw/flow-matching-posterior-estimation","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"found_in_text":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"0e2573db45f61f85","entry":"load_dataset","repo":"dingo-gw/flow-matching-posterior-estimation","repo_kind":"official","path":"sbi-benchmark/run_sbibm.py","file_url":"https://github.com/dingo-gw/flow-matching-posterior-estimation/blob/HEAD/sbi-benchmark/run_sbibm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e2573db45f61f85"}},{"code_sha256_prefix":"7d98fc0f6dc4c278","entry":"apply_func_with_multiprocessing","repo":"dingo-gw/dingo","repo_kind":"found_in_text","path":"dingo/core/multiprocessing.py","file_url":"https://github.com/dingo-gw/dingo/blob/HEAD/dingo/core/multiprocessing.py","link_basis":"first_harvest_node","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":"7d98fc0f6dc4c278"}},{"code_sha256_prefix":"4411e5ae14376a3a","entry":"check_equal_dict_of_arrays","repo":"dingo-gw/dingo","repo_kind":"found_in_text","path":"dingo/core/result.py","file_url":"https://github.com/dingo-gw/dingo/blob/HEAD/dingo/core/result.py","link_basis":"first_harvest_node","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":"4411e5ae14376a3a"}},{"code_sha256_prefix":"3e6dcf1f1a31bfcf","entry":"chunk_and_concat","repo":"dingo-gw/dingo","repo_kind":"found_in_text","path":"dingo/core/inference/composer.py","file_url":"https://github.com/dingo-gw/dingo/blob/HEAD/dingo/core/inference/composer.py","link_basis":"first_harvest_node","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":"3e6dcf1f1a31bfcf"}},{"code_sha256_prefix":"b9536168e2d5ca71","entry":"freeze","repo":"dingo-gw/dingo","repo_kind":"found_in_text","path":"dingo/core/result.py","file_url":"https://github.com/dingo-gw/dingo/blob/HEAD/dingo/core/result.py","link_basis":"first_harvest_node","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":"b9536168e2d5ca71"}},{"code_sha256_prefix":"b81decc0a23cd13b","entry":"get_default_nde_settings_3d","repo":"dingo-gw/dingo","repo_kind":"found_in_text","path":"dingo/core/density/nde_settings.py","file_url":"https://github.com/dingo-gw/dingo/blob/HEAD/dingo/core/density/nde_settings.py","link_basis":"first_harvest_node","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":"b81decc0a23cd13b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}