[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121797-en":3,"doc-seo-121797-105":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":20,"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},121797,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Application-Driven Development of Computational Tools and Algorithms for Machine Learning and Mean-Field Games - Research and Development","A dissertation on building computational tools and algorithms for optimization, machine learning, and mean-field games. It introduces MFGLib, an open-source Python library for solving Nash equilibria in generic mean-field games. It reformulates Nash-equilibrium search as non-convex optimization, then proposes occupation-time-adapted perturbations—PGDOT and PAGDOT—to escape saddle points with theoretical guarantees and numerical evidence. It also develops a stacking ensemble for detecting ophthalmology overutilization and healthcare fraud in Medicare.","UC Berkeley  \nUC Berkeley Electronic Theses and Dissertations  \nTitle  \nApplication-Driven Development of Computational Tools and Algorithms for Machine Learning and Mean-Field Games  \nPermalink  \n[https://escholarship.org/uc/item/8b39r1m1](https://escholarship.org/uc/item/8b39r1m1)  \nAuthor  \nTajrobehkar, Mahan  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nApplication-Driven Development of Computational Tools and Algorithms for Machine  \nLearning and Mean-Field Games  \nBy  \nMahan Tajrobehkar  \nA dissertation submitted in partial satisfaction of the  \nrequirements for the degree of  \nDoctor of Philosophy  \nin  \nEngineering-Industrial Engineering and Operations Research  \nin the  \nGraduate Division  \nof the  \nUniversity of California, Berkeley  \nCommittee in charge:  \nProfessor Xin Guo, Chair  \nProfessor Zeyu Zheng  \nProfessor Anant Sahai  \nSummer 2023  \nApplication-Driven Development of Computational Tools and Algorithms for Machine  \nLearning and Mean-Field Games  \nCopyright 2023  \nby  \nMahan Tajrobehkar  \n1  \nAbstract  \nApplication-Driven Development of Computational Tools and Algorithms for Machine  \nLearning and Mean-Field Games  \nby  \nMahan Tajrobehkar  \nDoctor of Philosophy in Engineering-Industrial Engineering and Operations Research  \nUniversity of California, Berkeley  \nProfessor Xin Guo, Chair  \nIn today’s rapidly evolving technological landscape, the development and advancement of computational tools and algorithms have become paramount across a wide range of research fields. This holds particularly true in various domains of computational mathematics, encompassing areas such as machine learning, optimization, and algorithmic game theory. The computational tools serve as essential enablers, empowering researchers and practitioners by facilitating efficient modeling, analysis, and prediction. Algorithms are essential components of computational tools, which provide instructions for data processing, pattern recognition, and decision-making.  \nThis dissertation focuses on developing computational tools and algorithms for specific applications in the interconnected fields of optimization, machine learning (ML), and meanfield games (MFGs) . First, to address the absence of a comprehensive computational tool for MFGs, we present MFGLib, an open-source Python library designed to provide a userfriendly and customizable interface for solving Nash equilibria in generic MFGs. Second, we demonstrate that the search for Nash equilibria in MFGs and various ML problems can be formulated as non-convex optimization problems, where the presence of saddle points significantly impedes the effectiveness of gradient descent algorithm and its variants. To help optimization algorithms escape saddle points efficiently, we introduce a novel perturbation mechanism based on the dynamics of vertex-repelling random walk. This leads to the development of two new algorithms, perturbed gradient descent adapted to occupation time (PGDOT) and its accelerated version (PAGDOT) . Theoretical guarantees for these algorithms are established, and through extensive numerical experiments, we showcase their superiority over several state-of-the-art optimization methods. Last, we explore a relatively independent machine learning task—detecting overutilization and fraud in healthcare. We focus on developing an ensemble model based on Stacked Generalization (stacking) to detect overutilization in Medicare within the field of Ophthalmology. Our results highlight  \n2  \nthe superiority of the stacking ensemble model over traditional ML models in accurately distinguishing overutilizing ophthalmologists from non-fraudulent ones.  \ni  \nTo my parents, for ensuring every educational opportunity was available to me.  \nii  \nContents  \nContents ii  \nList of Figures iv  \nList of Tables vii  \n1 Introduction 1  \n1. 1 Related Publications . . . . . . . ","cbCaipLUlXaIYwTG","https://ap.wps.com/l/cbCaipLUlXaIYwTG","pdf",24676837,1,111,"English","en",105,"# Introduction\n# MFGLib: A Library for Mean-Field Games\n## Related Work\n## Brief Overview of MFGLib\n## Future Work\n# Escaping Saddle Points Efficiently with Occupation-Time-Adapted Perturbations\n## Background and Existing Results\n## Main Results\n## Empirical Results\n## Conclusion\n# Leveraging Stacked Generalization to Effectively Detect Overutilization in Medicare\n## Data Source, Preprocessing, and Labeling\n## Overutilization Analysis via Machine Learning Techniques\n## Discussion\n## Limitations","[{\"question\":\"What is MFGLib and what problem does it address?\",\"answer\":\"MFGLib is an open-source Python library for solving Nash equilibria in generic mean-field games, designed to provide a user-friendly and customizable interface.\"},{\"question\":\"How are Nash equilibrium searches in mean-field games connected to optimization?\",\"answer\":\"They are reformulated as non-convex optimization problems, where saddle points hinder the effectiveness of gradient descent variants.\"},{\"question\":\"What do PGDOT and PAGDOT contribute to optimization?\",\"answer\":\"They introduce a perturbation mechanism based on vertex-repelling random walk dynamics, with theoretical guarantees and numerical experiments showing improved performance over state-of-the-art optimization methods.\"}]","Application-Driven Development of Computational Tools and Algorithms for Machine Learning and Mean-Field Games - Research and Development | PDF",1785806927,280,{"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},"application-driven-development-of-computational-tools-and-algorithms-for-machine-learning-and-mean-field-games-research-and-development","",{"@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/application-driven-development-of-computational-tools-and-algorithms-for-machine-learning-and-mean-field-games-research-and-development/121797/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is MFGLib and what problem does it address?","Question",{"text":75,"@type":76},"MFGLib is an open-source Python library for solving Nash equilibria in generic mean-field games, designed to provide a user-friendly and customizable interface.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are Nash equilibrium searches in mean-field games connected to optimization?",{"text":80,"@type":76},"They are reformulated as non-convex optimization problems, where saddle points hinder the effectiveness of gradient descent variants.",{"name":82,"@type":73,"acceptedAnswer":83},"What do PGDOT and PAGDOT contribute to optimization?",{"text":84,"@type":76},"They introduce a perturbation mechanism based on vertex-repelling random walk dynamics, with theoretical guarantees and numerical experiments showing improved performance over state-of-the-art optimization methods.","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"]