A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks

A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks | 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 A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks Minh-Duc Nguyen, Dung D. Le This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6802050/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 Pareto Set Learning (PSL) is popular as an efficient approach to obtaining the complete optimal solution in Multi-objective Learning (MOL). A set of optimal solutions approximates the Pareto set, and its mapping is a set of dense points in the Pareto front in objective space. However, some current methods face a challenge: how to make the Pareto solution is diverse while maximizing the hypervolume value. In this paper, we propose a novel method to address this challenge, which employs Stein Variational Gradient Descent (SVGD) to approximate the entire Paretoset. SVGD pushes a set of particles towards the Pareto set by applying a form of functional gradient descent, whichhelps to converge and diversify optimal solutions. Additionally, we employ diverse gradient direction strategies to thoroughly investigate a unified framework for SVGD in multi-objective optimization and adapt this framework with an annealing schedule to promote stability. We introduce our method, SVH-MOL, and validate its effectiveness through extensive experiments on multi-objective problems and multi-task learning, demonstrating its superior performance. Multi-objective Optimization Stein Variational Gradient Descent Pareto Front Learning Hypernet Full Text Additional Declarations No competing interests reported. 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-6802050","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":472497234,"identity":"8c89e215-5ece-439d-a5f2-ccee60728c81","order_by":0,"name":"Minh-Duc Nguyen","email":"","orcid":"","institution":"VinUniversity","correspondingAuthor":false,"prefix":"","firstName":"Minh-Duc","middleName":"","lastName":"Nguyen","suffix":""},{"id":472497235,"identity":"c3585bfc-e114-432c-8d63-b54b21324289","order_by":1,"name":"Dung D. Le","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3LMQrCMBSA4SeBTjFdWwr2Cq8EilAPExHs0kpHNxUP4NreokcoFOzSAwRcFBcHhx7AwRYVcYm6CeaHhOTxPgCd7hcruishAyDdAx+TtwQJ/56Ml68TRUzG5QkwCPOqv3WSBAZMCsNJFMSWs+kQMIzzkk2dFIHbHUkVBGXkI2AZZ2vqOxRhnEtBOP2AhPadLD4hfN8SYZIbEShF76gidn3227XQ2xDKA4qWl9WHlZKwKuJNMw9cw6y9Hb2MXFZNilJF2gxLPD9We3pLNQAgzbsNnU6n+/Ou6QVCisqUUxAAAAAASUVORK5CYII=","orcid":"","institution":"VinUniversity","correspondingAuthor":true,"prefix":"","firstName":"Dung","middleName":"D.","lastName":"Le","suffix":""}],"badges":[],"createdAt":"2025-06-02 12:08:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6802050/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6802050/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87094114,"identity":"8f9bf17e-8795-4b4d-9122-a4ee5f5ded8b","added_by":"auto","created_at":"2025-07-19 09:47:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1710968,"visible":true,"origin":"","legend":"","description":"","filename":"ACML2025JournalTrackfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6802050/v1_covered_f3744ce2-406b-469f-ad56-eaaa13d9d963.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Multi-objective Optimization, Stein Variational Gradient Descent, Pareto Front Learning, Hypernet","lastPublishedDoi":"10.21203/rs.3.rs-6802050/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6802050/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePareto Set Learning (PSL) is popular as an efficient approach to obtaining the complete optimal solution in Multi-objective Learning (MOL). A set of optimal solutions approximates the Pareto set, and its mapping is a set of dense points in the Pareto front in objective space. However, some current methods face a challenge: how to make the Pareto solution is diverse while maximizing the hypervolume value. In this paper, we propose a novel method to address this challenge, which employs Stein Variational Gradient Descent (SVGD) to approximate the entire Paretoset. SVGD pushes a set of particles towards the Pareto set by applying a form of functional gradient descent, whichhelps to converge and diversify optimal solutions. Additionally, we employ diverse gradient direction strategies to thoroughly investigate a unified framework for SVGD in multi-objective optimization and adapt this framework with an annealing schedule to promote stability. We introduce our method, SVH-MOL, and validate its effectiveness through extensive experiments on multi-objective problems and multi-task learning, demonstrating its superior performance.\u003c/p\u003e","manuscriptTitle":"A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-19 05:41:42","doi":"10.21203/rs.3.rs-6802050/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":"5f1ee17b-0069-4629-8620-4a5c06dd414f","owner":[],"postedDate":"June 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-19T09:38:54+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-19 05:41:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6802050","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6802050","identity":"rs-6802050","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}