{"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/unbalanced-sobolev-descent","title":"Unbalanced Sobolev Descent","arxiv_id":"2009.14148","date":"2020-09-29","proceeding":"NeurIPS 2020 12","authors":["Youssef Mroueh","Mattia Rigotti"],"abstract":"We introduce Unbalanced Sobolev Descent (USD), a particle descent algorithm for transporting a high dimensional source distribution to a target distribution that does not necessarily have the same mass. We define the Sobolev-Fisher discrepancy between distributions and show that it relates to advection-reaction transport equations and the Wasserstein-Fisher-Rao metric between distributions. USD transports particles along gradient flows of the witness function of the Sobolev-Fisher discrepancy (advection step) and reweighs the mass of particles with respect to this witness function (reaction step). The reaction step can be thought of as a birth-death process of the particles with rate of growth proportional to the witness function. When the Sobolev-Fisher witness function is estimated in a Reproducing Kernel Hilbert Space (RKHS), under mild assumptions we show that USD converges asymptotically (in the limit of infinite particles) to the target distribution in the Maximum Mean Discrepancy (MMD) sense. We then give two methods to estimate the Sobolev-Fisher witness with neural networks, resulting in two Neural USD algorithms. The first one implements the reaction step with mirror descent on the weights, while the second implements it through a birth-death process of particles. We show on synthetic examples that USD transports distributions with or without conservation of mass faster than previous particle descent algorithms, and finally demonstrate its use for molecular biology analyses where our method is naturally suited to match developmental stages of populations of differentiating cells based on their single-cell RNA sequencing profile. Code is available at https://github.com/ibm/usd .","url_abs":"https://arxiv.org/abs/2009.14148v1","url_pdf":"https://arxiv.org/pdf/2009.14148v1.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":"unbalanced-sobolev-descent","repo_url":"https://github.com/IBM/USD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.14148","atlas_url":"https://app.syntology.ai/?focus=2009.14148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14148"}},"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":"deterministic:regex_extraction","url":"https://github.com/ibm/usd","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/USD","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":2,"unverified":10},"by_repo_kind":{"official":{"samples":15,"ran":5,"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":"666b93c844016302","entry":"D_forward_weights","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"666b93c844016302"}},{"code_sha256_prefix":"a74a618e9386ec3d","entry":"MMD_RFF","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a74a618e9386ec3d"}},{"code_sha256_prefix":"7b1e4a57e169fde5","entry":"RFFEmbedding","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b1e4a57e169fde5"}},{"code_sha256_prefix":"1beaa0f96fbe0db6","entry":"get_loader","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1beaa0f96fbe0db6"}},{"code_sha256_prefix":"194fa2394685944b","entry":"minibatch","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"194fa2394685944b"}},{"code_sha256_prefix":"535e52d7bda9b841","entry":"describe_data","repo":"ibm/usd","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/ibm/usd/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"535e52d7bda9b841"}},{"code_sha256_prefix":"290087b87df2ac2e","entry":"get_devices","repo":"ibm/usd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ibm/usd/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"290087b87df2ac2e"}},{"code_sha256_prefix":"5912b3a04cff8c04","entry":"load_img","repo":"ibm/usd","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/ibm/usd/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5912b3a04cff8c04"}},{"code_sha256_prefix":"82adb6728cac0e04","entry":"load_weights","repo":"ibm/usd","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/ibm/usd/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82adb6728cac0e04"}},{"code_sha256_prefix":"88a867cdff5a2e0b","entry":"log_to_dict","repo":"ibm/usd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ibm/usd/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88a867cdff5a2e0b"}},{"code_sha256_prefix":"0b8190dcac4fd585","entry":"make_data_parallel","repo":"ibm/usd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ibm/usd/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b8190dcac4fd585"}},{"code_sha256_prefix":"13c848a877c3681a","entry":"manual_sgd_","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13c848a877c3681a"}},{"code_sha256_prefix":"8ae5e6dfcb32482c","entry":"sparsemax","repo":"ibm/usd","repo_kind":"official","path":"modules.py","file_url":"https://github.com/ibm/usd/blob/HEAD/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ae5e6dfcb32482c"}},{"code_sha256_prefix":"fc3718baf8f65341","entry":"swish","repo":"ibm/usd","repo_kind":"official","path":"modules.py","file_url":"https://github.com/ibm/usd/blob/HEAD/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc3718baf8f65341"}},{"code_sha256_prefix":"debaae28c8c3b426","entry":"train_unbalanced_descent","repo":"IBM/USD","repo_kind":"official","path":"unbalanced_descent.py","file_url":"https://github.com/IBM/USD/blob/HEAD/unbalanced_descent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"debaae28c8c3b426"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}