[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128553-en":3,"doc-seo-128553-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128553,549768064622,"Anda","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Trustworthy Machine Learning - From Algorithmic Transparency to Decision Support","Developing machine learning models that decision-makers can trust is essential for real-world deployment. The thesis examines how practitioners apply algorithmic transparency, including explainability and uncertainty estimates, in industry, revealing limited use for external stakeholders. To address this, it introduces new transparency methods tailored to decision contexts, validated through experiments with human decision-makers.","Trustworthy Machine Learning  \nFrom Algorithmic Transparency to Decision Support  \nUmang Sanjiv Bhatt  \nDepartment of Engineering  \nUniversity of Cambridge  \nThis dissertation is submitted for the degree of Doctor of Philosophy  \nSt. Edmund’s College September 2023  \nTo my Dada, Nareshchandra Maneklal Bhatt. I hope you are proud of what our Math Thinking  \nProcess has become.  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the Preface and specified in the text. I further state that no substantial part of my thesis has already been submitted, or, is being concurrently submitted for any such degree, diploma or other qualification at the University of Cambridge or any other University or similar institution except as declared in the Preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nUmang Sanjiv Bhatt September 2023  \nTrustworthy Machine Learning From Algorithmic Transparency to Decision Support  \nUmang Sanjiv Bhatt  \nDeveloping machine learning models worthy of decision-maker trust is crucial to using models in practice. Algorithmic transparency tools, such as explainability and uncertainty estimates, demonstrate the trustworthiness of a model to a decision-maker. In this thesis, we first explore how practitioners use explainability in industry. Through an interview study, we find that, while engineers increasingly use explainability methods to test model behavior during development, there is limited adoption of these methods for the benefit of external stakeholders. To that end, we develop novel algorithmic transparency methods for specific decision-making contextsand test these methods with real decision-makers via human-subject experiments. We first propose DIVINE, an example-based explanation method, which finds training points that are not only influential to the model’s parameters but also diversely located in input space. We show how our explanations can improve a decision-maker’s ability to simulate a model’s decision boundary. We next discuss Counterfactual Latent Uncertainty Explanations (CLUE), a feature importance explanation method that identifies which input features, if perturbed, would reduce the model’s uncertainty on a given input. We demonstrate how decision-makers can use our explanations to identify a model’s uncertainty on unseen inputs. While each method is successful in its own right, we are interested in understanding, more generally, the settings under which outcomes improve after a decision-maker leverages a form of decision support, beit algorithmic transparency or model predictions. We propose the problem of learning a decision support policy that, for a given input, chooses which form of support to provide to decisionmakers for whom we initially have no prior information. Using techniques from stochastic contextual bandits, we introduce THREAD, an online algorithm to personalize a decision support policy for each decision-maker. We deploy THREAD with real users to show how personalized policies can be learned online, and illustrate nuances of learning decision support policies in practice. We conclude this thesis with the promise of personalizing access to decision support, which could include forms of algorithmic transparency, based on decision-maker needs.  \nAcknowledgements  \nFirst and foremost, I want to thank Swaminarayan Bhagwan, God, for granting me the opportunity to a PhD. My gurus, Pramukh Swami Maharaj and Mahant Swami Maharaj, have supported every step of my spiritual and academic journey: for that, I am eternally indebted. Their gna (wishes) continue to make my decision-making all the more straightforward. “Pra¯rabdham metad ichchhaiva” —Satsang Diksha 45 .  \nI never thought I would do a PhD. At the end of my first year of undergrad at Carnegie Mellon University, I was smitten with the entrepreneurship world, yet my facu","cbCaij8I9JBXWUkE","https://ap.wps.com/l/cbCaij8I9JBXWUkE","pdf",17803032,3,1,254,"English","en",105,"# Research Background\n## Algorithmic Transparency and Trust\n# Methods and Contributions\n## DIVINE: Example-Based Explanations\n## CLUE: Counterfactual Latent Uncertainty Explanations\n## THREAD: Learning a Decision Support Policy\n# Validation and Deployment\n## Human-Subject Experiments\n## Online Personalization with Real Users\n# Conclusion","[{\"question\":\"What problem does the thesis focus on?\",\"answer\":\"It focuses on building machine learning models that earn decision-maker trust for practical use, leveraging algorithmic transparency such as explainability and uncertainty estimates.\"},{\"question\":\"What do the interview study findings reveal about explainability adoption?\",\"answer\":\"Engineers increasingly use explainability during development to test model behavior, but adoption for the benefit of external stakeholders remains limited.\"},{\"question\":\"How do the proposed methods support decision-makers?\",\"answer\":\"DIVINE provides example-based explanations to help decision-makers simulate a model’s decision boundary, while CLUE identifies which feature perturbations would reduce uncertainty on a specific input; THREAD then personalizes which form of support to provide using stochastic contextual bandits.\"}]","Trustworthy Machine Learning - From Algorithmic Transparency to Decision Support | PDF",1786001705,640,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"trustworthy-machine-learning-from-algorithmic-transparency-to-decision-support","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/trustworthy-machine-learning-from-algorithmic-transparency-to-decision-support/128553/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis focus on?","Question",{"text":76,"@type":77},"It focuses on building machine learning models that earn decision-maker trust for practical use, leveraging algorithmic transparency such as explainability and uncertainty estimates.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What do the interview study findings reveal about explainability adoption?",{"text":81,"@type":77},"Engineers increasingly use explainability during development to test model behavior, but adoption for the benefit of external stakeholders remains limited.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the proposed methods support decision-makers?",{"text":85,"@type":77},"DIVINE provides example-based explanations to help decision-makers simulate a model’s decision boundary, while CLUE identifies which feature perturbations would reduce uncertainty on a specific input; THREAD then personalizes which form of support to provide using stochastic contextual bandits.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]