{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/lagrangian-decomposition-for-neural-network","title":"Lagrangian Decomposition for Neural Network Verification","arxiv_id":"2002.10410","date":"2020-02-24","proceeding":null,"authors":["Rudy Bunel","Alessandro De Palma","Alban Desmaison","Krishnamurthy Dvijotham","Pushmeet Kohli","Philip H. S. Torr","M. Pawan Kumar"],"abstract":"A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even further, making the bounds unnecessarily loose. We propose a novel approach based on Lagrangian Decomposition. Our formulation admits an efficient supergradient ascent algorithm, as well as an improved proximal algorithm. Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds. Empirically, we show that we obtain bounds comparable with off-the-shelf solvers in a fraction of their running time, and obtain tighter bounds in the same time as previous dual algorithms. This results in an overall speed-up when employing the bounds for formal verification. Code for our algorithms is available at https://github.com/oval-group/decomposition-plnn-bounds.","url_abs":"https://arxiv.org/abs/2002.10410v3","url_pdf":"https://arxiv.org/pdf/2002.10410v3.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":"lagrangian-decomposition-for-neural-network","repo_url":"https://github.com/oval-group/decomposition-plnn-bounds","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lagrangian-decomposition-for-neural-network","repo_url":"https://github.com/oval-group/scaling-the-convex-barrier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.10410","atlas_url":"https://app.syntology.ai/?focus=2002.10410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10410"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.10410"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.10410"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.10410\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2002.10410"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2002.10410\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2002.10410"},"call":"get_concepts_for_paper(arxiv_id=\"2002.10410\")"}],"by_repo":[{"repo":"oval-group/decomposition-plnn-bounds","kind":"official","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"oval-group/scaling-the-convex-barrier","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2002.10410.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2002.10410.svg"},"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/oval-group/scaling-the-convex-barrier","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oval-group/decomposition-plnn-bounds","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":2},"n_samples":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":5,"ran":4,"n_ran_checked":4,"n_instrument":0,"repositories":1},"listed":{"samples":2,"ran":1,"n_ran_checked":0,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"afab9dc2ebdd02aa","code_sha256_prefix":"afab9dc2ebdd02aa","entry":"bdot","repo":"oval-group/decomposition-plnn-bounds","repo_kind":"official","path":"plnn_bounds/proxlp_solver/utils.py","file_url":"https://github.com/oval-group/decomposition-plnn-bounds/blob/HEAD/plnn_bounds/proxlp_solver/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"elt1:Tensor/2/float, elt2:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","retrieve_with":{"tool":"get_code","code_sha256":"afab9dc2ebdd02aa"},"code_page":"/code/bdot","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"afab9dc2ebdd02aa"}},{"code_sha256":"03249132743194cc","code_sha256_prefix":"03249132743194cc","entry":"bl2_norm","repo":"oval-group/decomposition-plnn-bounds","repo_kind":"official","path":"plnn_bounds/proxlp_solver/utils.py","file_url":"https://github.com/oval-group/decomposition-plnn-bounds/blob/HEAD/plnn_bounds/proxlp_solver/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"bv:Tensor/3/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","retrieve_with":{"tool":"get_code","code_sha256":"03249132743194cc"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"03249132743194cc"}},{"code_sha256":"c1b9258718b8fe48","code_sha256_prefix":"c1b9258718b8fe48","entry":"make_elided_models","repo":"oval-group/scaling-the-convex-barrier","repo_kind":"listed","path":"tools/bounding_tools/anderson_cifar_bound_comparison.py","file_url":"https://github.com/oval-group/scaling-the-convex-barrier/blob/HEAD/tools/bounding_tools/anderson_cifar_bound_comparison.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"model:callable/0/?, return_error:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c1b9258718b8fe48"}},{"code_sha256":"b4ad52a116df1451","code_sha256_prefix":"b4ad52a116df1451","entry":"opt_relu_pair","repo":"oval-group/decomposition-plnn-bounds","repo_kind":"official","path":"plnn_bounds/proxlp_solver/by_pairs.py","file_url":"https://github.com/oval-group/decomposition-plnn-bounds/blob/HEAD/plnn_bounds/proxlp_solver/by_pairs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"layer:callable/0/?, lin_hat_k:Tensor/2/float, lin_hat_kp1:Tensor/2/float, lb_k:Tensor/2/float, ub_k:Tensor/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b4ad52a116df1451"}},{"code_sha256":"1c49e5ae3f68bbc7","code_sha256_prefix":"1c49e5ae3f68bbc7","entry":"prod","repo":"oval-group/decomposition-plnn-bounds","repo_kind":"official","path":"plnn_bounds/proxlp_solver/utils.py","file_url":"https://github.com/oval-group/decomposition-plnn-bounds/blob/HEAD/plnn_bounds/proxlp_solver/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"elts:list/1/int","fixture_out_type":"int","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1c49e5ae3f68bbc7"},"code_page":"/code/prod","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1c49e5ae3f68bbc7"}},{"code_sha256":"9980cffefb52e0f4","code_sha256_prefix":"9980cffefb52e0f4","entry":"cifar_loaders","repo":"oval-group/scaling-the-convex-barrier","repo_kind":"listed","path":"tools/bounding_tools/anderson_cifar_bound_comparison.py","file_url":"https://github.com/oval-group/scaling-the-convex-barrier/blob/HEAD/tools/bounding_tools/anderson_cifar_bound_comparison.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9980cffefb52e0f4"}},{"code_sha256":"298cf2a3ecfce374","code_sha256_prefix":"298cf2a3ecfce374","entry":"opt_lin_domain","repo":"oval-group/decomposition-plnn-bounds","repo_kind":"official","path":"plnn_bounds/proxlp_solver/by_pairs.py","file_url":"https://github.com/oval-group/decomposition-plnn-bounds/blob/HEAD/plnn_bounds/proxlp_solver/by_pairs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"298cf2a3ecfce374"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2be34cda0f1143c928e3721248c430d13ed314794e45bbc81f9b2adf8b91a3d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}