{"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/robust-and-provably-monotonic-networks","title":"Robust and Provably Monotonic Networks","arxiv_id":"2112.00038","date":"2021-11-30","proceeding":null,"authors":["Ouail Kitouni","Niklas Nolte","Mike Williams"],"abstract":"The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep learning models that can also be generalized to other architectures. The method relies on a simple weight normalization scheme during training that ensures the Lipschitz constant of every layer is below an upper limit specified by the analyst. A simple monotonic residual connection can then be used to make the model monotonic in any subset of its inputs, which is useful in scenarios where domain knowledge dictates such dependence. Examples can be found in algorithmic fairness requirements or, as presented here, in the classification of the decays of subatomic particles produced at the CERN Large Hadron Collider. Our normalization is minimally constraining and allows the underlying architecture to maintain higher expressiveness compared to other techniques which aim to either control the Lipschitz constant of the model or ensure its monotonicity. We show how the algorithm was used to train a powerful, robust, and interpretable discriminator for heavy-flavor-quark decays, which has been adopted for use as the primary data-selection algorithm in the LHCb real-time data-processing system in the current LHC data-taking period known as Run 3. In addition, our algorithm has also achieved state-of-the-art performance on benchmarks in medicine, finance, and other applications.","url_abs":"https://arxiv.org/abs/2112.00038v2","url_pdf":"https://arxiv.org/pdf/2112.00038v2.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":[],"tasks":[{"task_slug":"fairness","task_name":"Fairness"}],"methods":[{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.00038","atlas_url":"https://app.syntology.ai/?focus=2112.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00038"}},"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/niklasnolte/MonotoneNorm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":6,"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":"8615c1319fcdc41d","entry":"direct_norm","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/functional.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/functional.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8615c1319fcdc41d"}},{"code_sha256_prefix":"ad616dd13e06dcbd","entry":"get_normed_weights","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/functional.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/functional.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad616dd13e06dcbd"}},{"code_sha256_prefix":"82f832134263ab1b","entry":"get_sorting_shape","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/group.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/group.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82f832134263ab1b"}},{"code_sha256_prefix":"79dbba877ef46e9c","entry":"group_sort","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/group.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/group.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79dbba877ef46e9c"}},{"code_sha256_prefix":"c2b71c9d5b16bb36","entry":"project_norm","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/functional.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/functional.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2b71c9d5b16bb36"}},{"code_sha256_prefix":"cc9786ab2e19cf12","entry":"train","repo":"niklasnolte/MonotoneNorm","repo_kind":"found_in_text","path":"monotonicnetworks/tests.py","file_url":"https://github.com/niklasnolte/MonotoneNorm/blob/HEAD/monotonicnetworks/tests.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc9786ab2e19cf12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}