[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121327-en":3,"doc-seo-121327-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121327,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Privacy-preserving distributed machine learning for artificial intelligence of things - Doctoral thesis","This thesis proposes fully distributed machine learning algorithms that run over ad-hoc networks of machines or agents. Distributed learning is required when centralized processing is infeasible due to computing and communication costs, while privacy risks arise from curious network members and eavesdroppers. The work develops distributed learning methods for AI of Things with intrinsic privacy-preserving properties, including privacy-preserving learning under horizontal and feature partitioning and distributed optimization based on ADMM.","Doctoral theses at NTNU, 2023:12  \nCristiano Gratton  \nPrivacy-preserving distributed machine learning for artificial intelligence of things  \nDoctora l thesis  \nNT NU  \nNorwegian University of Science and Technology Thesis for the Degree of Ph ilosophiae Doctor  \nFaculty of Informat ion Technology and Electrical Engineering  \nDepartment of Electronic Systems  \nCristiano Gratton  \nPrivacy-preserving distributed machine learning for artificial intelligence of things  \nThesis for the Degree of Philosophiae Doctor Trondheim, January 2023  \nNorwegian University of Science and Technology  \nFaculty of Information Technology and Electrical Engineering Department of Electronic Systems  \nNTNU  \nNorwegian University of Science and Technology Thesis for the Degree of Philosophiae Doctor  \nFaculty of Information Technology and Electrical Engineering Department of Electronic Systems  \n© Cristiano Gratton  \nISBN 978-82-326-5563-2 (printed ver.)  \nISBN 978-82-326-6584-6 (electronic ver.)  \nISSN 1503-8181 (printed ver.)  \nISSN 2703-8084 (online ver.) Doctoral theses at NTNU, 2023:12 Printed by NTNU Grafisk senter  \nAbstract  \nThis thesis proposes machine learning algorithms that can be fully distributed over ad-hoc networks of machines/agents. Developing distributed algorithms for artificial intelligence is necessary since running machine-learning-based data analyticson a single central hub may be unfeasible due to computing/communication costs. In the context of distributed learning, privacy violation risks due to curious members of the network or eavesdroppers make the development of privacy-preserving distributed algorithms imperative.  \nThe main contributions of the thesis are around developing distributed machine learning algorithms for artificial intelligence of things including distributed algorithms with intrinsic privacy-preserving properties. In particular, the contributions can be grouped in the following categories:  \n• distributed learning over networks with horizontal/row partitioning of data  \n• intrinsically privacy-preserving distributed learning with zeroth-order optimization  \n• distributed learning over networks with vertical/feature partitioning of data. In the context of distributed learning with horizontal partitioning of data, we propose a new distributed algorithm to solve the total least-squares (TLS) problem anda privacy-preserving distributed algorithm to minimize a regularized empirical risk function when the first-order information is not available.  \nWe show that the latter algorithm has intrinsic privacy-preserving properties. Most existing privacy-preserving distributed optimization/estimation algorithms exploit some perturbation mechanism to preserve privacy, which comes at the cost of reduced accuracy. Contrarily, we exploit the inherent randomness due to the use of a  \nzeroth-order method and show that this stochasticity is sufficient to ensure differential privacy. Moreover, we demonstrate that the proposed algorithm outperforms the existing differentially-private ones in terms of accuracy while yielding similar privacy guarantees.  \nIn the context of distributed learning with feature partitioning of data, we develop a new distributed algorithm to solve the ridge regression problem. Subsequently, we develop a new algorithm that is designed for an `2-norm-square cost function with non-smooth regularizers. Finally, we develop a new consensus-based distributed algorithm for solving learning problems when the data is distributed among agents in feature partitions and computing the conjugate of the possibly non-smooth cost or regularizer functions is challenging or unfeasible. The proposed algorithm is designed for optimizing generic non-smooth objective functions over arbitrary graphs without using or computing any conjugate function. All the above-mentioned algorithms are fully-distributed and based on the alternating direction method of multipliers (ADMM) that is suitable for distributed optimization thanks to i","cbCaieIa5WNtNmM7","https://ap.wps.com/l/cbCaieIa5WNtNmM7","pdf",5803167,1,188,"English","en",105,"# 1 Introduction\n## 1.1 Objectives\n## 1.2 Methodology\n## 1.3 Thesis Contributions\n## 1.4 Thesis Organization\n# 2 Distributed Optimization and Privacy\n## 2.1 Distributed Optimization\n## 2.2 The Alternating Direction Method of Multipliers","[{\"question\":\"Why are distributed machine learning algorithms needed in this thesis?\",\"answer\":\"Centralized data processing may be infeasible because of computing and communication costs. Distributed learning also enables modeling across networks of agents rather than a single hub.\"},{\"question\":\"What privacy threats motivate the research?\",\"answer\":\"Privacy can be violated by curious network members or eavesdroppers. The thesis therefore develops privacy-preserving distributed algorithms with explicit guarantees.\"},{\"question\":\"How does the thesis achieve differential privacy for distributed learning with horizontal partitioning?\",\"answer\":\"It uses intrinsic randomness from a zeroth-order method rather than external perturbation. The stochasticity is shown to be sufficient to ensure differential privacy while maintaining accuracy.\"}]","Privacy-preserving distributed machine learning for artificial intelligence of things - Doctoral thesis | PDF",1785735086,474,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"privacy-preserving-distributed-machine-learning-for-artificial-intelligence-of-things-doctoral-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/privacy-preserving-distributed-machine-learning-for-artificial-intelligence-of-things-doctoral-thesis/121327/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are distributed machine learning algorithms needed in this thesis?","Question",{"text":75,"@type":76},"Centralized data processing may be infeasible because of computing and communication costs. Distributed learning also enables modeling across networks of agents rather than a single hub.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What privacy threats motivate the research?",{"text":80,"@type":76},"Privacy can be violated by curious network members or eavesdroppers. The thesis therefore develops privacy-preserving distributed algorithms with explicit guarantees.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis achieve differential privacy for distributed learning with horizontal partitioning?",{"text":84,"@type":76},"It uses intrinsic randomness from a zeroth-order method rather than external perturbation. The stochasticity is shown to be sufficient to ensure differential privacy while maintaining accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]