{"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/direct-parameterization-of-lipschitz-bounded","title":"Direct Parameterization of Lipschitz-Bounded Deep Networks","arxiv_id":"2301.11526","date":"2023-01-27","proceeding":null,"authors":["Ruigang Wang","Ian R. Manchester"],"abstract":"This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed $\\ell^2$ Lipschitz bounds, i.e. limited sensitivity to input perturbations. The Lipschitz guarantees are equivalent to the tightest-known bounds based on certification via a semidefinite program (SDP). We provide a ``direct'' parameterization, i.e., a smooth mapping from $\\mathbb R^N$ onto the set of weights satisfying the SDP-based bound. Moreover, our parameterization is complete, i.e. a neural network satisfies the SDP bound if and only if it can be represented via our parameterization. This enables training using standard gradient methods, without any inner approximation or computationally intensive tasks (e.g. projections or barrier terms) for the SDP constraint. The new parameterization can equivalently be thought of as either a new layer type (the \\textit{sandwich layer}), or a novel parameterization of standard feedforward networks with parameter sharing between neighbouring layers. A comprehensive set of experiments on image classification shows that sandwich layers outperform previous approaches on both empirical and certified robust accuracy. Code is available at \\url{https://github.com/acfr/LBDN}.","url_abs":"https://arxiv.org/abs/2301.11526v3","url_pdf":"https://arxiv.org/pdf/2301.11526v3.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":"direct-parameterization-of-lipschitz-bounded","repo_url":"https://github.com/acfr/lbdn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"direct-parameterization-of-lipschitz-bounded","repo_url":"https://github.com/acfr/RobustNeuralNetworks.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.11526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11526"}},"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":"deterministic:regex_extraction","url":"https://github.com/acfr/LBDN","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acfr/lbdn","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acfr/RobustNeuralNetworks.jl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"adde6a231e077970","entry":"cayley","repo":"acfr/lbdn","repo_kind":"official","path":"layer.py","file_url":"https://github.com/acfr/lbdn/blob/HEAD/layer.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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"adde6a231e077970"}},{"code_sha256_prefix":"7f65e2f329ec52db","entry":"cayley","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7f65e2f329ec52db"}},{"code_sha256_prefix":"0f03f3173ccf90cd","entry":"fft_shift_matrix","repo":"acfr/lbdn","repo_kind":"official","path":"layer.py","file_url":"https://github.com/acfr/lbdn/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0f03f3173ccf90cd"}},{"code_sha256_prefix":"4abdc9cbdc6342f4","entry":"SandwichConv","repo":"acfr/lbdn","repo_kind":"official","path":"layer.py","file_url":"https://github.com/acfr/lbdn/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4abdc9cbdc6342f4"}},{"code_sha256_prefix":"1fa94c6602979fac","entry":"StridedConv","repo":"acfr/lbdn","repo_kind":"official","path":"layer.py","file_url":"https://github.com/acfr/lbdn/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1fa94c6602979fac"}},{"code_sha256_prefix":"33452b7ae0f9f563","entry":"fft_shift_matrix","repo":"acfr/lbdn","repo_kind":"official","path":"layer.py","file_url":"https://github.com/acfr/lbdn/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"33452b7ae0f9f563"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}