Joint Structure-Function Neural Architecture Optimization under Resource Constraints

Joint Structure-Function Neural Architecture Optimization under Resource Constraints | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Joint Structure-Function Neural Architecture Optimization under Resource Constraints Lianhua Wang, Meilin Xu, Jiawen Chen, Yucheng Li, Zhou Shen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7460435/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The rapid evolution of artificial intelligence (AI) necessitates the development of efficient neural architectures that balance performance and resource constraints. This paper introduces a novel Joint Structure-Function Optimization (JSFO) framework designed to simultaneously optimize the structural components and functional parameters of neural networks. Traditional neural architecture search (NAS) methods often treat architecture and parameter optimization as disjointed processes, leading to suboptimal results. Our framework integrates discrete architecture search with continuous parameter tuning, effectively addressing the inherent interdependencies between these two facets within a unified resource constraint paradigm. We present rigorous mathematical formulations and a structured optimization algorithm that allows for the exploration of a vast search space, resulting in high-performing models suitable for deployment on resource-constrained platforms. Experimental results on benchmark datasets, including CIFAR-10 and ImageNet, demonstrate substantial improvements in the accuracy-resource trade-off compared to state-of-the-art NAS approaches. The JSFO framework not only enhances model performance but also ensures adaptability to varying operational constraints, making it a crucial advancement in practical AI applications. This research lays the groundwork for future innovations in neural architecture design and optimization, promoting more accessible and efficient deployment of AI technologies across diverse environments. Neural Architecture Optimization Resource-Constrained Learning Structure-Function Co-evolution Discrete-Continuous Optimization Automated Machine Learning (AutoML). Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7460435","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":505677230,"identity":"c7f86da6-da3c-4630-b4a4-65a1f4bb1985","order_by":0,"name":"Lianhua Wang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Lianhua","middleName":"","lastName":"Wang","suffix":""},{"id":505677231,"identity":"d6238280-09d5-49be-a1f6-e05c1e7e4574","order_by":1,"name":"Meilin Xu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Meilin","middleName":"","lastName":"Xu","suffix":""},{"id":505677232,"identity":"01aa5a0e-402d-4e29-af2d-dcc8d4c48c44","order_by":2,"name":"Jiawen Chen","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jiawen","middleName":"","lastName":"Chen","suffix":""},{"id":505677233,"identity":"87d9d738-0867-45f6-9768-cc5a05632a5e","order_by":3,"name":"Yucheng Li","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yucheng","middleName":"","lastName":"Li","suffix":""},{"id":505677234,"identity":"7700e4cd-1b45-4bab-a7d6-2c61054fa070","order_by":4,"name":"Zhou Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIiWNgGAWjYDACCSBmbEASMGAH8QwsSNHCcwBESpCiRSIBJo4dyM9uPvbw5w6bxAbpw4c/fKi5J28u+fzqhh8FEgz87d0J2LQY3DmWbiB5Ji2xgS8tTXLGsWLDnbNzym72AB0mcebsBqxaJHLMJAzbDic28PCYMfOwJSQY3M5Ju8ED1GIgkYtVi/yM/G8SiWAt/J8///kH1HLzTNrNP3i0MNzIYZM4CLGFQZqxDajlBvux2/hsMbiRZibZ2JZm3MbDZibZ25dguOFMDtttGQMJHlx+kZ+R/EzyZ5uNbD8P8+MPP74lyBscP/7s5ps/NnL87b3YHQYDbAgmjwGYxKscDbA/IEX1KBgFo2AUDH8AAA8DYpsNUdNBAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Zhou","middleName":"","lastName":"Shen","suffix":""}],"badges":[],"createdAt":"2025-08-26 08:21:23","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7460435/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7460435/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90077217,"identity":"828962cf-1430-4982-a859-c348275c7db6","added_by":"auto","created_at":"2025-08-28 08:11:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":229936,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7460435/v1_covered_1542e4be-4e52-4062-b74c-5ed7d93a23fe.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eJoint Structure-Function Neural Architecture Optimization under Resource Constraints\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Neural Architecture Optimization, Resource-Constrained Learning, Structure-Function Co-evolution, Discrete-Continuous Optimization, Automated Machine Learning (AutoML).","lastPublishedDoi":"10.21203/rs.3.rs-7460435/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7460435/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid evolution of artificial intelligence (AI) necessitates the development of efficient neural architectures that balance performance and resource constraints. This paper introduces a novel Joint Structure-Function Optimization (JSFO) framework designed to simultaneously optimize the structural components and functional parameters of neural networks. Traditional neural architecture search (NAS) methods often treat architecture and parameter optimization as disjointed processes, leading to suboptimal results. Our framework integrates discrete architecture search with continuous parameter tuning, effectively addressing the inherent interdependencies between these two facets within a unified resource constraint paradigm. We present rigorous mathematical formulations and a structured optimization algorithm that allows for the exploration of a vast search space, resulting in high-performing models suitable for deployment on resource-constrained platforms. Experimental results on benchmark datasets, including CIFAR-10 and ImageNet, demonstrate substantial improvements in the accuracy-resource trade-off compared to state-of-the-art NAS approaches. The JSFO framework not only enhances model performance but also ensures adaptability to varying operational constraints, making it a crucial advancement in practical AI applications. This research lays the groundwork for future innovations in neural architecture design and optimization, promoting more accessible and efficient deployment of AI technologies across diverse environments.\u003c/p\u003e","manuscriptTitle":"Joint Structure-Function Neural Architecture Optimization under Resource Constraints","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-28 08:03:48","doi":"10.21203/rs.3.rs-7460435/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ed81d30f-bcb1-4766-8ad1-01209863f3ff","owner":[],"postedDate":"August 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-28T08:03:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-28 08:03:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7460435","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7460435","identity":"rs-7460435","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}