{"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-wasserstein-gradient-flows-for-maximum","title":"Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels","arxiv_id":"2301.11624","date":"2023-01-27","proceeding":null,"authors":["Fabian Altekrüger","Johannes Hertrich","Gabriele Steidl"],"abstract":"Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely. In this paper we contribute to the understanding of such flows. We propose to approximate the backward scheme of Jordan, Kinderlehrer and Otto for computing such Wasserstein gradient flows as well as a forward scheme for so-called Wasserstein steepest descent flows by neural networks (NNs). Since we cannot restrict ourselves to absolutely continuous measures, we have to deal with transport plans and velocity plans instead of usual transport maps and velocity fields. Indeed, we approximate the disintegration of both plans by generative NNs which are learned with respect to appropriate loss functions. In order to evaluate the quality of both neural schemes, we benchmark them on the interaction energy. Here we provide analytic formulas for Wasserstein schemes starting at a Dirac measure and show their convergence as the time step size tends to zero. Finally, we illustrate our neural MMD flows by numerical examples.","url_abs":"https://arxiv.org/abs/2301.11624v3","url_pdf":"https://arxiv.org/pdf/2301.11624v3.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-wasserstein-gradient-flows-for-maximum","repo_url":"https://github.com/fabianaltekrueger/neuralwassersteingradientflows","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=2301.11624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11624"}},"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/fabianaltekrueger/neuralwassersteingradientflows","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"19677bbf9f508e54","entry":"NeuralBackwardScheme","repo":"fabianaltekrueger/neuralwassersteingradientflows","repo_kind":"official","path":"schemes/NeuralBackwardScheme.py","file_url":"https://github.com/fabianaltekrueger/neuralwassersteingradientflows/blob/HEAD/schemes/NeuralBackwardScheme.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19677bbf9f508e54"}},{"code_sha256_prefix":"2db9229a67eb6839","entry":"W2_term","repo":"fabianaltekrueger/neuralwassersteingradientflows","repo_kind":"official","path":"schemes/NeuralBackwardScheme.py","file_url":"https://github.com/fabianaltekrueger/neuralwassersteingradientflows/blob/HEAD/schemes/NeuralBackwardScheme.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2db9229a67eb6839"}},{"code_sha256_prefix":"3874f41b591aad93","entry":"get_network","repo":"fabianaltekrueger/neuralwassersteingradientflows","repo_kind":"official","path":"schemes/NeuralBackwardScheme.py","file_url":"https://github.com/fabianaltekrueger/neuralwassersteingradientflows/blob/HEAD/schemes/NeuralBackwardScheme.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3874f41b591aad93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}