{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd2-2174"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd2-2174","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Refining the Inverse Lipschitz Constant for Injective ReLU Networks","abstract":"In this thesis, we study the Inverse Lipschitz Constant (ILC) of injective ReLU layers. We study the tightness of the ILC lower bound established in Puthawala et al. Our approach has three components. First, we find that the conditions for injectivity on lines yield a weaker condition than the general condition given in Puthawala et al. Second, we perform numerical experiments to judge the tightness of the existing ILC lower bound and find that bound is overly conservative. Third, we identify the source of the potential slack in the proof of the existing ILC bound, and perform further numerical experiments to support this hypothesis. An accurate ILC is crucial for better understanding and potentially reducing the network’s sensitivity to input variations, which is essential for improving the performance and stability of neural networks in real-world applications.","abstract_html":"In this thesis, we study the Inverse Lipschitz Constant (ILC) of injective ReLU layers. We study the tightness of the ILC lower bound established in Puthawala et al. Our approach has three components. First, we find that the conditions for injectivity on lines yield a weaker condition than the general condition given in Puthawala et al. Second, we perform numerical experiments to judge the tightness of the existing ILC lower bound and find that bound is overly conservative. Third, we identify the source of the potential slack in the proof of the existing ILC bound, and perform further numerical experiments to support this hypothesis. An accurate ILC is crucial for better understanding and potentially reducing the network’s sensitivity to input variations, which is essential for improving the performance and stability of neural networks in real-world applications.","abstract_has_math":false,"creators":["Rausch, Cole"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Mathematics and Statistics","degree_department":null,"school":null,"contributors":["Michael Puthawala"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:04:49Z","subjects":["Mathematics","Statistics and Probability"],"languages":[],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd2/1175","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd2/1175","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd2-2174","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Michael Puthawala"]},{"key":"dc:creator","label":"Author","values":["Rausch, Cole"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2024-08-22T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mathematics and Statistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Mathematics","Statistics and Probability"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openprairie.sdstate.edu/etd2/1175"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we study the Inverse Lipschitz Constant (ILC) of injective ReLU layers. We study the tightness of the ILC lower bound established in Puthawala et al. Our approach has three components. First, we find that the conditions for injectivity on lines yield a weaker condition than the general condition given in Puthawala et al. Second, we perform numerical experiments to judge the tightness of the existing ILC lower bound and find that bound is overly conservative. Third, we identify the source of the potential slack in the proof of the existing ILC bound, and perform further numerical experiments to support this hypothesis. An accurate ILC is crucial for better understanding and potentially reducing the network’s sensitivity to input variations, which is essential for improving the performance and stability of neural networks in real-world applications."]},{"key":"dc:title","label":"Title","values":["Refining the Inverse Lipschitz Constant for Injective ReLU Networks"]}]}],"canonical_facts":{"dc:contributor":["Michael Puthawala"],"dc:creator":["Rausch, Cole"],"dc:date.available":["2024-08-22T07:00:00Z"],"dc:date.created":["2024-01-01T08:00:00Z"],"dc:description.abstract":["In this thesis, we study the Inverse Lipschitz Constant (ILC) of injective ReLU layers. We study the tightness of the ILC lower bound established in Puthawala et al. Our approach has three components. First, we find that the conditions for injectivity on lines yield a weaker condition than the general condition given in Puthawala et al. Second, we perform numerical experiments to judge the tightness of the existing ILC lower bound and find that bound is overly conservative. Third, we identify the source of the potential slack in the proof of the existing ILC bound, and perform further numerical experiments to support this hypothesis. An accurate ILC is crucial for better understanding and potentially reducing the network’s sensitivity to input variations, which is essential for improving the performance and stability of neural networks in real-world applications."],"dc:identifier":["https://openprairie.sdstate.edu/etd2/1175"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Mathematics","Statistics and Probability"],"dc:title":["Refining the Inverse Lipschitz Constant for Injective ReLU Networks"],"thesis:degree_discipline":["Mathematics and Statistics"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:04:49Z"}