{"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/kernel-stein-discrepancy-descent","title":"Kernel Stein Discrepancy Descent","arxiv_id":"2105.09994","date":"2021-05-20","proceeding":null,"authors":["Anna Korba","Pierre-Cyril Aubin-Frankowski","Szymon Majewski","Pierre Ablin"],"abstract":"Among dissimilarities between probability distributions, the Kernel Stein Discrepancy (KSD) has received much interest recently. We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution $\\pi$ on $\\mathbb{R}^d$, known up to a normalization constant. This leads to a straightforwardly implementable, deterministic score-based method to sample from $\\pi$, named KSD Descent, which uses a set of particles to approximate $\\pi$. Remarkably, owing to a tractable loss function, KSD Descent can leverage robust parameter-free optimization schemes such as L-BFGS; this contrasts with other popular particle-based schemes such as the Stein Variational Gradient Descent algorithm. We study the convergence properties of KSD Descent and demonstrate its practical relevance. However, we also highlight failure cases by showing that the algorithm can get stuck in spurious local minima.","url_abs":"https://arxiv.org/abs/2105.09994v1","url_pdf":"https://arxiv.org/pdf/2105.09994v1.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":"kernel-stein-discrepancy-descent","repo_url":"https://github.com/pierreablin/ksddescent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"kernel-stein-discrepancy-descent","repo_url":"https://github.com/louissharrock/coin-svgd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.09994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09994"}},"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/louissharrock/coin-svgd","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pierreablin/ksddescent","reach":null}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"38fcabf75695b25c","entry":"amari_distance","repo":"pierreablin/ksddescent","repo_kind":"official","path":"examples/plot_ica.py","file_url":"https://github.com/pierreablin/ksddescent/blob/HEAD/examples/plot_ica.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38fcabf75695b25c"}},{"code_sha256_prefix":"708e579a3c9b0c9f","entry":"ksdd_gradient","repo":"pierreablin/ksddescent","repo_kind":"official","path":"ksddescent/ksd_descent.py","file_url":"https://github.com/pierreablin/ksddescent/blob/HEAD/ksddescent/ksd_descent.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":"708e579a3c9b0c9f"}},{"code_sha256_prefix":"367287d4dd15ce81","entry":"ksdd_lbfgs","repo":"pierreablin/ksddescent","repo_kind":"official","path":"ksddescent/ksd_descent.py","file_url":"https://github.com/pierreablin/ksddescent/blob/HEAD/ksddescent/ksd_descent.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":"367287d4dd15ce81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}