[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117000-en":3,"doc-seo-117000-105":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},117000,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Theoretical Foundations of Trustworthy Machine Learning","The dissertation develops theoretical foundations for trustworthy machine learning with a focus on robustness. It studies when non-parametric methods are robust, establishing conditions that guarantee stability of learning under adversarial perturbations. The work proposes consistent non-parametric approaches aimed at maximizing robustness, analyzes sample complexity for robust linear classification on separated data, and provides results for robust empirical risk minimization with tolerance. Validation discussions and convergence guarantees support the theoretical claims.","UC San Diego  \nUC San Diego Electronic Theses and Dissertations  \nTitle  \nTheoretical Foundations of Trustworthy Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/50b3n2d3](https://escholarship.org/uc/item/50b3n2d3)  \nAuthor  \nBhattacharjee, Robi  \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  \nTheoretical Foundations of Trustworthy Machine Learning  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy  \nin  \nComputer Science  \nby  \nRobi Bhattacharjee  \nCommittee in charge:  \nProfessor Kamalika Chaudhuri, Chair  \nProfessor Mikhail Belkin  \nProfessor Sanjoy Dasgupta  \nProfessor Yoav Freund  \nCopyright  \nRobi Bhattacharjee, 2023 All rights reserved.  \nThe Dissertation of Robi Bhattacharjee is approved, and it is acceptable in quality and form for publication on microfilm and electronically.  \nUniversity of California San Diego  \n2023  \nDEDICATION  \nFor Mom, Dad, and Sormeh.  \nTABLE OF CONTENTS  \nDissertation Approval Page .................................................... iii  \nDedication .................................................................. iv  \nTable of Contents ............................................................ v  \nList of Figures ............................................................... ix  \nList of Tables ................................................................ xi  \nAcknowledgements ........................................................... xii  \nVita ........................................................................ xiv  \nAbstract of the Dissertation .................................................... xv  \nIntroduction ................................................................. 1  \nChapter 1 When are Non-Parametric Methods Robust? .......................... 3  \n1.1 Introduction ......................................................... 3  \n1.1.1 Related Work ................................................. 5  \n1.2 Preliminaries ........................................................ 6  \n1.2.1 Setting ....................................................... 6  \n1.2.2 Notions of Consistency ......................................... 7  \n1.2.3 Non-parametric Classifiers ...................................... 10  \n1.3 Warm Up: r-separated distributions ..................................... 12  \n1.4 General Distributions ................................................. 16  \n1.4.1 The r-Optimal Classifier and Adversarial Pruning ................... 16  \n1.4.2 Convergence Guarantees ........................................ 17  \n1.5 Validation ........................................................... 19  \n1.5.1 Experimental Setup ............................................ 20  \n1.5.2 Results ....................................................... 21  \n1.5.3 Discussion .................................................... 21  \n1.6 Conclusion .......................................................... 22  \n1.7 Acknowledgment ..................................................... 22  \nChapter 2 Consistent Non-Parametric Methods for Maximizing Robustness ........ 23  \n2.1 Introduction ......................................................... 23  \n2.2 Preliminaries ........................................................ 26  \n2.3 The Neighborhood preserving Bayes optimal classifier ..................... 28  \n2.3.1 Neighborhood Consistency ...................................... 31  \n2.4 Neighborhood Consistent Non-Parametric Classifiers ....................... 32  \n2.4.1 Splitting Numbers ............................................. 33  \n2.4.2 Sufficient Conditions for Neighborhood Consistency ................ 34  \n2.4.3 Nearest Neighbors and Kernel Classifiers .......................... 35  \n2.4.4 Histogram Classifiers ........................................... 36  ","cbCaijQICqTfflHt","https://ap.wps.com/l/cbCaijQICqTfflHt","pdf",1933914,1,270,"English","en",105,"# Introduction\n# Chapter 1 When are Non-Parametric Methods Robust?\n## Preliminaries and Validation\n# Chapter 2 Consistent Non-Parametric Methods for Maximizing Robustness\n## Neighborhood Consistency and Validation\n# Chapter 3 Sample Complexity of Robust Linear Classification on Separated Data\n## Lower and Upper Bounds\n# Chapter 4 Robust Empirical Risk Minimization with Tolerance\n## Tolerant PAC Learning and Linear Classifiers","[{\"question\":\"What question does the dissertation address about trustworthy machine learning?\",\"answer\":\"It investigates how robustness can be guaranteed in learning algorithms, especially for non-parametric and linear classification settings under adversarial or tolerant regimes.\"},{\"question\":\"How are non-parametric methods studied in Chapter 1?\",\"answer\":\"Chapter 1 examines conditions under which non-parametric classifiers are robust, including preliminaries, consistency-related notions, and validation through experimental setup and results.\"},{\"question\":\"What topics are covered in later chapters on robustness theory?\",\"answer\":\"Chapter 2 develops consistent non-parametric methods for maximizing robustness; Chapter 3 analyzes sample complexity for robust linear classification on separated data; Chapter 4 studies robust empirical risk minimization with tolerance and tolerant PAC learning.\"}]","Theoretical Foundations of Trustworthy Machine Learning | PDF",1785673029,680,{"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},"theoretical-foundations-of-trustworthy-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/theoretical-foundations-of-trustworthy-machine-learning/117000/",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","2026-08-02",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 question does the dissertation address about trustworthy machine learning?","Question",{"text":75,"@type":76},"It investigates how robustness can be guaranteed in learning algorithms, especially for non-parametric and linear classification settings under adversarial or tolerant regimes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are non-parametric methods studied in Chapter 1?",{"text":80,"@type":76},"Chapter 1 examines conditions under which non-parametric classifiers are robust, including preliminaries, consistency-related notions, and validation through experimental setup and results.",{"name":82,"@type":73,"acceptedAnswer":83},"What topics are covered in later chapters on robustness theory?",{"text":84,"@type":76},"Chapter 2 develops consistent non-parametric methods for maximizing robustness; Chapter 3 analyzes sample complexity for robust linear classification on separated data; Chapter 4 studies robust empirical risk minimization with tolerance and tolerant PAC learning.","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"]