[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123741-en":3,"doc-seo-123741-105":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},123741,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","On Distributed Learning Techniques for Machine Learning","Dissertation on distributed learning methods for machine learning, focusing on federated learning under heterogeneous and non-IID data. It develops curriculum-based strategies for clients, including effects of scoring and pacing functions, data heterogeneity levels, and curriculum design choices such as difficulty-based partitioning and expert- vs self-guided curricula. It further studies clustered federated learning using client inference similarity and introduces FLIS and PACFL, with experiments and convergence or consistency analyses, culminating in practical implementation considerations.","UC San Diego  \nUC San Diego Electronic Theses and Dissertations  \nTitle  \nOn Distributed Learning Techniques for Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/0hj2d2cw](https://escholarship.org/uc/item/0hj2d2cw)  \nAuthor  \nVahidian, Saeed  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA SAN DIEGO  \nOn Distributed Learning Techniques for Machine Learning  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy  \nin  \nElectrical Engineering (Signal & Image Processing)  \nby  \nSaeed Vahidian  \nCommittee in charge:  \nProfessor Bill Lin, Chair  \nProfessor Philip E. Gill  \nProfessor Yuanyuan Shi  \nProfessor Hao Su  \nProfessor Xiaolong Wang  \nCopyright  \nSaeed Vahidian, 2023 All rights reserved.  \nThe Dissertation of Saeed Vahidian is approved, and it is acceptable in quality and form for publication on microfilm and electronically.  \nUniversity of California San Diego  \n2023  \nDEDICATION  \nTo My Beloved Heavenly Parents: Ali ibn Abi Talib (Imam Amir al-Mu’minin) and Fatemeh al-Zahra  \n&  \nTo My Beloved Earthly Parents: Malek-Hossein and Ashraf.  \nEPIGRAPH  \nThe most valuable of all treasures is knowledge, and the worst of all losses is ignorance.  \nImam Hossein (son of Ali ibn Abi Talib)  \nTABLE OF CONTENTS  \nDissertation Approval Page .................................................... iii  \nDedication .................................................................. iv  \nEpigraph .................................................................... v  \n[Table of Contents ............................................................ vi](Table of Contents ............................................................ vi)  \n[List of Figures ............................................................... ix](List of Figures ............................................................... ix)  \n[List of Tables ................................................................ xvi](List of Tables ................................................................ xvi)  \n[List of Algorithms ............................................................ xx](List of Algorithms ............................................................ xx)  \n[Acknowledgements ........................................................... xxi](Acknowledgements ........................................................... xxi)  \n[Vita ........................................................................ xxiii](Vita ........................................................................ xxiii)  \nAbstract of the Dissertation .................................................... xxv  \nChapter 1 Introduction ..................................................... 1  \n1.1 Dissertation Organization .............................................. 2  \nChapter 2 Curricula in Federated Learning .................................... 6  \n2.1 Introduction ......................................................... 6  \n2.2 Related Work ........................................................ 8  \n2.3 Curriculum Components ............................................... 9  \n2.4 Experiment .......................................................... 10  \n2.4.1 Effect of scoring function in IID and Non-IID FL ................... 12  \n2.4.2 Effect of pacing function and its parameters in IID and Non-IID FL .... 14  \n2.4.3 Effect of level of data heterogeneity ............................... 15  \n2.5 Effect of amount of data on clients end ................................... 19  \n2.6 Curriculum on Clients ................................................. 19  \n2.6.1 Motivation .................................................... 20  \n2.6.2 Client Curriculum .............................................. 21  \n2.6.3 Difficulty based partitioning ..................................... 23  ","cbCaibk3VW9ICMIz","https://ap.wps.com/l/cbCaibk3VW9ICMIz","pdf",10930894,1,207,"English","en",105,"# Chapter 1 Introduction\n## Dissertation Organization\n# Chapter 2 Curricula in Federated Learning\n## Introduction\n## Related Work\n## Curriculum Components\n## Experiment\n## Theoretical Analysis and Convergence Guarantees\n## Implementation Details\n## Conclusion\n# Chapter 3 Clustered Federated Learning\n## Introduction\n## Background and Related Work\n## FLIS\n## PACFL\n# Chapter 4 Personalized Federated Learning by Structured and Unstructured Pruning\n## Introduction","[{\"question\":\"What problem does the dissertation address in distributed machine learning?\",\"answer\":\"It studies distributed learning techniques in the federated learning setting, especially under non-IID and heterogeneous client data.\"},{\"question\":\"How does the dissertation incorporate curricula into federated learning?\",\"answer\":\"It proposes curriculum components and client-side curriculum strategies, analyzing how scoring and pacing functions and data heterogeneity affect performance.\"},{\"question\":\"What are FLIS and PACFL, and what do they aim to improve?\",\"answer\":\"FLIS clusters clients by inference similarity and PACFL extends clustered federated learning, supported by experiments and convergence or consistency analyses.\"}]","On Distributed Learning Techniques for Machine Learning | PDF",1785818280,522,{"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},"on-distributed-learning-techniques-for-machine-learning","",{"@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/on-distributed-learning-techniques-for-machine-learning/123741/",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","2026-08-04",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},"What problem does the dissertation address in distributed machine learning?","Question",{"text":75,"@type":76},"It studies distributed learning techniques in the federated learning setting, especially under non-IID and heterogeneous client data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation incorporate curricula into federated learning?",{"text":80,"@type":76},"It proposes curriculum components and client-side curriculum strategies, analyzing how scoring and pacing functions and data heterogeneity affect performance.",{"name":82,"@type":73,"acceptedAnswer":83},"What are FLIS and PACFL, and what do they aim to improve?",{"text":84,"@type":76},"FLIS clusters clients by inference similarity and PACFL extends clustered federated learning, supported by experiments and convergence or consistency analyses.","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"]