{"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/sorting-out-lipschitz-function-approximation","title":"Sorting out Lipschitz function approximation","arxiv_id":"1811.05381","date":"2018-11-13","proceeding":null,"authors":["Cem Anil","James Lucas","Roger Grosse"],"abstract":"Training neural networks under a strict Lipschitz constraint is useful for provable adversarial robustness, generalization bounds, interpretable gradients, and Wasserstein distance estimation. By the composition property of Lipschitz functions, it suffices to ensure that each individual affine transformation or nonlinear activation is 1-Lipschitz. The challenge is to do this while maintaining the expressive power. We identify a necessary property for such an architecture: each of the layers must preserve the gradient norm during backpropagation. Based on this, we propose to combine a gradient norm preserving activation function, GroupSort, with norm-constrained weight matrices. We show that norm-constrained GroupSort architectures are universal Lipschitz function approximators. Empirically, we show that norm-constrained GroupSort networks achieve tighter estimates of Wasserstein distance than their ReLU counterparts and can achieve provable adversarial robustness guarantees with little cost to accuracy.","url_abs":"https://arxiv.org/abs/1811.05381v2","url_pdf":"https://arxiv.org/pdf/1811.05381v2.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":"sorting-out-lipschitz-function-approximation","repo_url":"https://github.com/cemanil/LNets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.05381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05381"}},"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/cemanil/LNets","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"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":3,"samples":[{"code_sha256_prefix":"b511c85abf94d829","entry":"check_group_sorted","repo":"cemanil/LNets","repo_kind":"listed","path":"lnets/models/activations/group_sort.py","file_url":"https://github.com/cemanil/LNets/blob/HEAD/lnets/models/activations/group_sort.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b511c85abf94d829"}},{"code_sha256_prefix":"f3c2f30ec36e34f9","entry":"group_sort","repo":"cemanil/LNets","repo_kind":"listed","path":"lnets/models/activations/group_sort.py","file_url":"https://github.com/cemanil/LNets/blob/HEAD/lnets/models/activations/group_sort.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3c2f30ec36e34f9"}},{"code_sha256_prefix":"162ffe5c4e7ac47c","entry":"process_group_size","repo":"cemanil/LNets","repo_kind":"listed","path":"lnets/models/activations/group_sort.py","file_url":"https://github.com/cemanil/LNets/blob/HEAD/lnets/models/activations/group_sort.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"162ffe5c4e7ac47c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}