[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121535-en":3,"doc-seo-121535-105":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},121535,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","On Values in Fairness Optimization with Machine Learning - Abstract","Fairness criteria in statistical learning are widely debated, yet they illuminate the multiobjective character of many predictive modeling tasks. This paper examines how both epistemic and non-epistemic values shape the design of machine learning algorithms that optimize multiple normative goals at once. It centers on a key optimization design choice: biased search methods that encode objective priorities versus unbiased methods that do not, arguing both yield Pareto optimal solutions while additional values guide rational selection among them.","On Values in Fairness Optimization with Machine Learning  \nHeather Champion  \nDepartment of Philosophy, University of Western Ontario Rotman Institute of Philosophy, London, Ontario  \n[hchampi2@uwo.ca](hchampi2@uwo.ca)  \nAbstract  \nStatistical criteria of fairness, though controversial, bring attention to the multiobjective nature of many predictive modelling problems. In this paper, I consider how epistemic and non-epistemic values impact the design of machine learning algorithms that optimize for more than one normative goal. I focus on a major design choice between biased search strategies that directly incorporate priorities for various objectives into an optimization procedure, and unbiased search strategies that do not. I argue that both reliably generate Pareto optimal solutions such that various other values are relevant to making a rational choice between them.  \n1. Introduction  \nPhilosophers and computer scientists debate whether there exist statistical criteria of fairness that can be used to assess the fairness of a machine learning (ML) model’s predictions. In this paper, I bring attention to the additional values that are involved when these or other notions of fairness are integrated into an optimization procedure used to train an ML model. I focus on a major design choice in multiobjective optimization problems (MOOPs) between biased and unbiased search strategies, which are distinguished by whether they use priorities for the objectives to direct an optimization procedure. I argue that both reliably generate Pareto optimal (PO) solutions, but there are various additional, not purely epistemic, reasons to prefer one or the other.  \nThe paper will proceed as follows. In Section 2, I explain how my analysis diverges from existing philosophical work on algorithms and values, and I specify the sense in which I consider values to impact model design choices. In Section 3 , I introduce MOOPs and strategies for solving them, and I motivate why it is important to understand fairness optimization as a MOOP. In Section 4, I argue that the methodological choice between biased and unbiased search strategies is unforced by the epistemic aim of finding Pareto optimal tradeoffs. In Section 5, I discuss what additional values are relevant to this choice.  \n2. Values act as justificatory reasons for choices in optimization problems  \nPhilosophers and social scientists have brought critical attention to the multitude of ways that algorithms are biased, often leading to unfairness when algorithmic predictions inform decisions. In this work, I offer a novel philosophical reflection on how algorithms implement values by focusing on the choice of what optimization method to use when incorporating fairness notions into ML design. This goes beyond existing philosophical work that highlights the relationship between values and statistical performance metric(s) including tradeoffs between statistical criteria of fairness, and data-driven practices as a whole (e.g. Fazelpour and Danks 2021) . While fairness criteria can be incorporated at various stages of ML model design, including before, during, or after an optimization algorithm is run to train an ML model, my purpose here is to compare approaches that incorporate fairness notions into optimization design.  \nAs my goal is to analyze what justifies particular design choices in optimization, I will focus on a specific type of relation between values and choices where values act as justificatory reasons for choices. This type of relation is distinguished by Ward (2021), who characterizes itas involving an appeal to values in rational arguments used to support a certain course of action. Using Ward’s taxonomy: I will not attempt to answer what values motivate ML designers to choose various optimization strategies, which would require a separate psychological and sociological analysis. I will also not consider how values act as causes or effects of design choices; for instance, what valu","cbCaieHV2Gt4AOTN","https://ap.wps.com/l/cbCaieHV2Gt4AOTN","pdf",433094,1,14,"English","en",105,"# Abstract\n# Introduction\n# Values act as justificatory reasons for choices in optimization problems\n# Optimizing for fairness in ML is a multiobjective problem","[{\"question\":\"What is the main focus of the paper on values and fairness optimization?\",\"answer\":\"The paper analyzes how epistemic and non-epistemic values affect machine learning algorithm design when optimizing for more than one normative goal, especially within fairness contexts.\"},{\"question\":\"What is the key design choice compared in multiobjective fairness optimization?\",\"answer\":\"It contrasts biased search strategies that incorporate priorities for objectives in the optimization procedure with unbiased search strategies that do not.\"},{\"question\":\"Why does the paper argue fairness optimization is naturally a multiobjective problem?\",\"answer\":\"Because fairness-related predictive modeling involves tradeoffs across different cost/benefit considerations, so optimizing any fairness notion within ML typically requires handling multiple objectives simultaneously.\"}]","On Values in Fairness Optimization with Machine Learning - Abstract | PDF",1785736131,35,{"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-values-in-fairness-optimization-with-machine-learning-abstract","",{"@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-values-in-fairness-optimization-with-machine-learning-abstract/121535/",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 is the main focus of the paper on values and fairness optimization?","Question",{"text":75,"@type":76},"The paper analyzes how epistemic and non-epistemic values affect machine learning algorithm design when optimizing for more than one normative goal, especially within fairness contexts.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the key design choice compared in multiobjective fairness optimization?",{"text":80,"@type":76},"It contrasts biased search strategies that incorporate priorities for objectives in the optimization procedure with unbiased search strategies that do not.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the paper argue fairness optimization is naturally a multiobjective problem?",{"text":84,"@type":76},"Because fairness-related predictive modeling involves tradeoffs across different cost/benefit considerations, so optimizing any fairness notion within ML typically requires handling multiple objectives simultaneously.","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"]