{"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/beyond-the-single-neuron-convex-barrier-for","title":"Beyond the Single Neuron Convex Barrier for Neural Network Certification","arxiv_id":null,"date":"2019-12-01","proceeding":"NeurIPS 2019 12","authors":["Gagandeep Singh","Rupanshu Ganvir","Markus Püschel","Martin Vechev"],"abstract":"We propose a new parametric framework, called k-ReLU, for computing precise\nand scalable convex relaxations used to certify neural networks. The key idea is to\napproximate the output of multiple ReLUs in a layer jointly instead of separately.\nThis joint relaxation captures dependencies between the inputs to different ReLUs\nin a layer and thus overcomes the convex barrier imposed by the single neuron\ntriangle relaxation and its approximations. The framework is parametric in the\nnumber of k ReLUs it considers jointly and can be combined with existing verifiers\nin order to improve their precision. Our experimental results show that k-ReLU en-\nables significantly more precise certification than existing state-of-the-art verifiers\nwhile maintaining scalability.","url_abs":"http://papers.nips.cc/paper/9646-beyond-the-single-neuron-convex-barrier-for-neural-network-certification","url_pdf":"http://papers.nips.cc/paper/9646-beyond-the-single-neuron-convex-barrier-for-neural-network-certification.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":"beyond-the-single-neuron-convex-barrier-for","repo_url":"https://github.com/eth-sri/eran","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}