{"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/fast-approximation-of-the-sliced-wasserstein","title":"Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections","arxiv_id":"2106.15427","date":"2021-06-29","proceeding":"NeurIPS 2021 12","authors":["Kimia Nadjahi","Alain Durmus","Pierre E. Jacob","Roland Badeau","Umut Şimşekli"],"abstract":"The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational and statistical benefits. Since it is defined as an expectation over random projections, SW is commonly approximated by Monte Carlo. We adopt a new perspective to approximate SW by making use of the concentration of measure phenomenon: under mild assumptions, one-dimensional projections of a high-dimensional random vector are approximately Gaussian. Based on this observation, we develop a simple deterministic approximation for SW. Our method does not require sampling a number of random projections, and is therefore both accurate and easy to use compared to the usual Monte Carlo approximation. We derive nonasymptotical guarantees for our approach, and show that the approximation error goes to zero as the dimension increases, under a weak dependence condition on the data distribution. We validate our theoretical findings on synthetic datasets, and illustrate the proposed approximation on a generative modeling problem.","url_abs":"https://arxiv.org/abs/2106.15427v2","url_pdf":"https://arxiv.org/pdf/2106.15427v2.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":"fast-approximation-of-the-sliced-wasserstein","repo_url":"https://github.com/kimiandj/fast_sw","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-approximation-of-the-sliced-wasserstein","repo_url":"https://github.com/FlorentinCDX/Fast-Approx-SW","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.15427","atlas_url":"https://app.syntology.ai/?focus=2106.15427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.15427"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/FlorentinCDX/Fast-Approx-SW","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kimiandj/fast_sw","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"91ce0e6db1365a2f","entry":"m_2","repo":"FlorentinCDX/Fast-Approx-SW","repo_kind":"listed","path":"sw_approx.py","file_url":"https://github.com/FlorentinCDX/Fast-Approx-SW/blob/HEAD/sw_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91ce0e6db1365a2f"}},{"code_sha256_prefix":"218af1cb95cd9a34","entry":"sw_approx","repo":"FlorentinCDX/Fast-Approx-SW","repo_kind":"listed","path":"sw_approx.py","file_url":"https://github.com/FlorentinCDX/Fast-Approx-SW/blob/HEAD/sw_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"218af1cb95cd9a34"}},{"code_sha256_prefix":"cbda6eafb0afede0","entry":"wasserstein1d","repo":"kimiandj/fast_sw","repo_kind":"official","path":"swg/utils.py","file_url":"https://github.com/kimiandj/fast_sw/blob/HEAD/swg/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cbda6eafb0afede0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}