[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119395-en":3,"doc-seo-119395-105":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},119395,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Inductive Biases in Multi-Stage Machine Learning Problems and Applications","This dissertation investigates how inductive biases shape multi-stage machine learning systems where preprocessing, training, and adaptation occur across multiple steps and decisions unfold over time. Because such pipelines can mask bias effects on final performance, the work provides theoretical motivation and empirical validation for several bias mechanisms. It studies batch active learning for graph-based semi-supervised learning, stratification in non-negative matrix factorization and tensor factorization via efficient multiplicative-update methods, topological message-passing to mitigate oversquashing, and zero-shot context generalization in reinforcement learning.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nInductive Biases in Multi-Stage Machine Learning Problems and Applications  \nPermalink  \n[https://escholarship.org/uc/item/9h370546](https://escholarship.org/uc/item/9h370546)  \nAuthor  \nChapman, James Emory  \nPublication Date  \n2025  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA  \nLos Angeles  \nInductive Biases in Multi-Stage Machine Learning Problems and Applications  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Mathematics  \nby  \nJames Emory Chapman  \n2025  \n© Copyright by James Emory Chapman 2025  \nABSTRACT OF THE DISSERTATION  \nInductive Biases in Multi-Stage  \nMachine Learning Problems and Applications  \nby  \nJames Emory Chapman  \nDoctor of Philosophy in Mathematics  \nUniversity of California, Los Angeles, 2025  \nProfessor Andrea Bertozzi, Co-Chair Professor Guido Francisco Montúfar Cuartas, Co-Chair  \nThis thesis explores the role of inductive biases in multi-stage machine learning problems. Modern machine learning often involves multiple steps of preprocessing, training, and adaptation and models may be deployed to make many decisions over time. These complex pipelines can obscure the impact of specific biases in the final model’s performance. In chapter 2, we investigate the role of batch active learning in graph-based semi-supervised learning. Through theoretical motivation and empirical validation, we demonstrate improved accuracy and efficiency. In chapters 3 and 4, we investigate the role of stratification in non-negative matrix factorization and tensor factorization. We develop efficient multiplicative-update algorithmsand demonstrate their effectiveness on synthetic and real-world datasets. In chapter 5, we investigate the role of topological message-passing in relational structures. We propose a unifying framework for topological message-passing networks and demonstrate its effectiveness in mitigating oversquashing. This framework unifies many topological deep learning (TDL) methods under a common axiomatic framework, allowing for consistent theoretical analysis  \nand greater understanding of the algebraic and topological tools employed in TDL. In chapter 6, we investigate the role of zero-shot context generalization in reinforcement learning. We propose a novel method for zero-shot context generalization and demonstrate its effectiveness in improving model performance. This provides a straight-forward extension of many off-policy reinforcement learning methods, which improves generalization to unseen contexts. Through these investigations, we provide a comprehensive theoretical and empirical analysis of the aforementioned inductive biases in multi-stage machine learning problems. Our findings highlight the critical role of these biases in enhancing model performance and their broad applicability across diverse domains.  \nThe dissertation of James Emory Chapman is approved.  \nStanley J. Osher  \nArashAliAmini  \nGuido Francisco Montúfar Cuartas, Committee Co-Chair Andrea Bertozzi, Committee Co-Chair  \nUniversity of California, Los Angeles 2025  \nTo my parents, who have always believed in me and taught me the value of perseverance and hard work.  \nv  \nTABLE OF CONTENTS  \n1 Introduction ............................................ 1  \n2 Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets ................................................. 5  \n2.1 Introduction .......................................... 6  \n2.2 Math Background ....................................... 9  \n2.2.1 Data Embeddings ................................... 9  \n2.2.2 Graph Construction ................................. 10  \n2.2.3 Graph Learning .................................... 12  \n2.2.4 Active Learning .................................... 13  \n2.3 Core-Set Selec","cbCaiqNwsTqLvgLJ","https://ap.wps.com/l/cbCaiqNwsTqLvgLJ","pdf",5271053,1,240,"English","en",105,"# 1 Introduction\n# 2 Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets\n# 3 Stratified-NMF for Heterogeneous Data\n# 4 Stratified Non-Negative Tensor Factorization\n# 5 Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in","[{\"question\":\"What problem does the dissertation focus on regarding inductive biases?\",\"answer\":\"It examines how inductive biases affect multi-stage machine learning problems, where complex pipelines can obscure the influence of specific biases on final performance.\"},{\"question\":\"Which inductive bias is studied in chapter 2?\",\"answer\":\"Chapter 2 investigates batch active learning in graph-based semi-supervised learning, combining theoretical motivation with empirical validation to improve accuracy and efficiency.\"},{\"question\":\"What is developed to address oversquashing in relational structures?\",\"answer\":\"The dissertation proposes a unifying framework for topological message-passing networks and shows its effectiveness in mitigating oversquashing through consistent theoretical analysis.\"}]","Inductive Biases in Multi-Stage Machine Learning Problems and Applications | PDF",1785724084,605,{"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},"inductive-biases-in-multi-stage-machine-learning-problems-and-applications","",{"@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/inductive-biases-in-multi-stage-machine-learning-problems-and-applications/119395/",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},"What problem does the dissertation focus on regarding inductive biases?","Question",{"text":75,"@type":76},"It examines how inductive biases affect multi-stage machine learning problems, where complex pipelines can obscure the influence of specific biases on final performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which inductive bias is studied in chapter 2?",{"text":80,"@type":76},"Chapter 2 investigates batch active learning in graph-based semi-supervised learning, combining theoretical motivation with empirical validation to improve accuracy and efficiency.",{"name":82,"@type":73,"acceptedAnswer":83},"What is developed to address oversquashing in relational structures?",{"text":84,"@type":76},"The dissertation proposes a unifying framework for topological message-passing networks and shows its effectiveness in mitigating oversquashing through consistent theoretical analysis.","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"]