{"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/learning-latent-permutations-with-gumbel","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","arxiv_id":"1802.08665","date":"2018-02-23","proceeding":"ICLR 2018 1","authors":["Gonzalo Mena","David Belanger","Scott Linderman","Jasper Snoek"],"abstract":"Permutations and matchings are core building blocks in a variety of latent\nvariable models, as they allow us to align, canonicalize, and sort data.\nLearning in such models is difficult, however, because exact marginalization\nover these combinatorial objects is intractable. In response, this paper\nintroduces a collection of new methods for end-to-end learning in such models\nthat approximate discrete maximum-weight matching using the continuous Sinkhorn\noperator. Sinkhorn iteration is attractive because it functions as a simple,\neasy-to-implement analog of the softmax operator. With this, we can define the\nGumbel-Sinkhorn method, an extension of the Gumbel-Softmax method (Jang et al.\n2016, Maddison2016 et al. 2016) to distributions over latent matchings. We\ndemonstrate the effectiveness of our method by outperforming competitive\nbaselines on a range of qualitatively different tasks: sorting numbers, solving\njigsaw puzzles, and identifying neural signals in worms.","url_abs":"http://arxiv.org/abs/1802.08665v1","url_pdf":"http://arxiv.org/pdf/1802.08665v1.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":"learning-latent-permutations-with-gumbel","repo_url":"https://github.com/google/gumbel_sinkhorn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-latent-permutations-with-gumbel","repo_url":"https://github.com/HeddaCohenIndelman/Learning-Gumbel-Sinkhorn-Permutations-w-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.08665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08665"}},"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/HeddaCohenIndelman/Learning-Gumbel-Sinkhorn-Permutations-w-Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/gumbel_sinkhorn","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"0333e85f0ad554ad","entry":"kendall_tau","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"sinkhorn_ops.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/sinkhorn_ops.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":"0333e85f0ad554ad"}},{"code_sha256_prefix":"3f1ab6103613b1de","entry":"matching","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"sinkhorn_ops.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/sinkhorn_ops.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":"3f1ab6103613b1de"}},{"code_sha256_prefix":"b1d6f8bcfaec6f24","entry":"restore_checkpoint_if_exists","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"sorting/sorting_eval.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/sorting/sorting_eval.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":"b1d6f8bcfaec6f24"}},{"code_sha256_prefix":"f4b5cb2c941d138e","entry":"sample_gumbel","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"sinkhorn_ops.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/sinkhorn_ops.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":"f4b5cb2c941d138e"}},{"code_sha256_prefix":"a66e302bfd882730","entry":"set_optimizer","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"optimizer.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/optimizer.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":"a66e302bfd882730"}},{"code_sha256_prefix":"e3783afe5ced98c5","entry":"wait_for_new_checkpoint","repo":"google/gumbel_sinkhorn","repo_kind":"official","path":"sorting/sorting_eval.py","file_url":"https://github.com/google/gumbel_sinkhorn/blob/HEAD/sorting/sorting_eval.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":"e3783afe5ced98c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}