[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118689-en":3,"doc-seo-118689-105":30,"detail-sidebar-cat-0-en-105":95},{"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},118689,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Incentive-Aware Machine Learning for Social Welfare Maximization under Uncertainty - Dissertation","Machine Learning algorithms support high-stakes decisions in domains such as hiring, education, and medical trials, but they also change individuals’ incentives and strategic behavior. This dissertation studies incentive-aware machine learning under uncertainty from a centralized social planner’s perspective, where decision-subjects may act based on self-interest rather than algorithmic guidance. The work designs mechanisms that align subjects’ incentives with the planner’s goal of maximizing total social welfare. It focuses on incentivized exploration for online recommender systems, and further analyzes strategic learning, incentive design for collaborative learning participation, and robust downstream prediction under uncertainty.","Incentive-Aware Machine Learning for Social Welfare Maximization under Uncertainty  \nA DISSERTATION  \nSUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL OF THE UNIVERSITY OF MINNESOTA  \nBY  \nDung (Daniel) Ngo  \nIN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF  \nDOCTOR OF PHILOSOPHY  \nZhiwei Steven Wu, Maria Gini  \nNovember, 2024  \n© Dung (Daniel) Ngo 2024 ALL RIGHTS RESERVED  \nAcknowledgements  \nI want to convey my heartfelt thanks to everyone who has supported me throughout the process of completing this dissertation. I am incredibly grateful to my advisors, Zhiwei Steven Wu and Maria Gini, for their unwavering support and guidance. Their mentorship extended beyond academic advice, equipping me with essential skills in and out of research. Under Steven Wu’s direction, I had the opportunity to engage in intriguing projects and collaborate with exceptional individuals. He has also been an outstanding role model for my work ethic and a constant inspiration for my research.  \nMoreover, the unwavering support from my family and peers at the University of Minnesota and Carnegie Mellon University has been a guiding light during this challenging journey.  \nDedicated to my family and friends.  \nAbstract  \nMachine Learning algorithms are being deployed to aid the decision-making process of high-stakes domains such as hiring, education, and medical trials. Under the influence of these substantial algorithmic decisions, individuals (i. e. , the decision-subjects) are more aware of their role and capabilities in dictating the outcome of Machine Learning algorithms. On the other hand, the social planner (i. e. , the decision-maker) deploying these machine learning algorithms has to consider the incentives of individuals who are unwilling to follow the algorithmic decisions given to them unquestioningly. This dissertation focuses on incentive-aware machine learning under uncertainty through the lens of a centralized social planner deploying the algorithms for decision-making.  \nNaturally, some tension exists between the goals of these different stakeholders: an individual’s action often springs from self-interested motives. At the same time, the social planner wants to optimize for better social welfare across all individuals in the population. Therefore, the primary focus of this dissertation is to design incentive-aware Machine Learning algorithms that align with the incentives of the decision-subjects while obtaining the desired total outcomes. Concretely, I study the problem of incentivized exploration in the context of online recommender systems, where the social planner can only provide signals to facilitate the individual’s action choices. Mainly, I extend the existing literature of incentivized exploration in three trajectories: structured action sets, heterogeneous populations, and practical applications.  \nBeyond incentivized exploration, this dissertation also examines other settings where incentives play an essential role in the agent’s decision-making process. First, I study the problem of strategic learning, where the decision-subjects are strategic and may modify their input to obtain a more favorable prediction outcome. Secondly, I examine how a centralized server can incentivize participation in a collaborative learning setting. Finally, I investigate the setting where the downstream decision-makers face uncertainty in choosing an accurate and loss-minimizing predictor suitable for their downstream task. These works bring a greater understanding of how to create incentive-aware machine learning algorithms under uncertainty that both (1) align with each decision-subject’s belief and (2) maximize cumulative social welfare.  \nContents  \nAcknowledgements i  \nAbstract iii  \nList of Figures xi  \n1 Introduction 1  \n2 Background and Related Work 5  \n2.1 Background: Incentivized Exploration ................... 5  \n2.2 Related Work ................................. 7  \n3 Incentivizing Combinatorial Bandit Exploration 15  \n3.","cbCaiuOhTrERP73r","https://ap.wps.com/l/cbCaiuOhTrERP73r","pdf",5125031,1,363,"English","en",105,"# Acknowledgements\n# Abstract\n# List of Figures\n# 1 Introduction\n# 2 Background and Related Work\n## 2.1 Background: Incentivized Exploration\n## 2.2 Related Work\n# 3 Incentivizing Combinatorial Bandit Exploration\n## 3.1 Introduction\n## 3.2 Problem Formulation and Preliminaries\n## 3.3 Thompson Sampling is BIC\n## 3.4 BIC algorithms for initial exploration\n# 4 Incentivizing Compliance with Algorithmic Instruments\n## 4.1 Introduction\n## 4.2 Treatment-Control Model\n## 4.3 Overcoming Complete Non-Compliance\n## 4.5 Combined Recommendation Policy\n# 5 Incentive-Aware Synthetic Control\n## 5.1 Introduction\n## 5.2 Model\n## 5.4 Incentivized Exploration for Synthetic Control\n## 5.8 Conclusion","[{\"question\":\"What is the central problem addressed in this dissertation?\",\"answer\":\"Designing incentive-aware machine learning algorithms under uncertainty so that individuals’ incentives align with the centralized social planner’s objective of maximizing total social welfare.\"},{\"question\":\"How does the dissertation model decision-making between individuals and the social planner?\",\"answer\":\"It distinguishes decision-subjects (individuals whose actions may follow self-interested motives) from the social planner (the decision-maker deploying the algorithms) that must account for these incentives when optimizing outcomes.\"},{\"question\":\"Which application area receives a primary focus?\",\"answer\":\"Incentivized exploration in online recommender systems, where the planner provides signals to guide individuals’ action choices.\"},{\"question\":\"Besides incentivized exploration, what other incentive-driven settings are studied?\",\"answer\":\"Strategic learning where subjects can manipulate inputs, incentive design for participation in collaborative learning, and uncertainty-aware downstream prediction for loss-minimizing decision-making.\"}]","Incentive-Aware Machine Learning for Social Welfare Maximization under Uncertainty - Dissertation | PDF",1785684900,915,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"incentive-aware-machine-learning-for-social-welfare-maximization-under-uncertainty-dissertation","",{"@graph":36,"@context":89},[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/incentive-aware-machine-learning-for-social-welfare-maximization-under-uncertainty-dissertation/118689/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is the central problem addressed in this dissertation?","Question",{"text":75,"@type":76},"Designing incentive-aware machine learning algorithms under uncertainty so that individuals’ incentives align with the centralized social planner’s objective of maximizing total social welfare.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation model decision-making between individuals and the social planner?",{"text":80,"@type":76},"It distinguishes decision-subjects (individuals whose actions may follow self-interested motives) from the social planner (the decision-maker deploying the algorithms) that must account for these incentives when optimizing outcomes.",{"name":82,"@type":73,"acceptedAnswer":83},"Which application area receives a primary focus?",{"text":84,"@type":76},"Incentivized exploration in online recommender systems, where the planner provides signals to guide individuals’ action choices.",{"name":86,"@type":73,"acceptedAnswer":87},"Besides incentivized exploration, what other incentive-driven settings are studied?",{"text":88,"@type":76},"Strategic learning where subjects can manipulate inputs, incentive design for participation in collaborative learning, and uncertainty-aware downstream prediction for loss-minimizing decision-making.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]