[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117379-en":3,"doc-seo-117379-105":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},117379,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning for Computational Optimization - Doctor of Philosophy Dissertation","Machine learning techniques are applied to optimize the cost–quality trade-off in computationally constrained scientific modeling. The thesis addresses the mismatch between rapidly growing computational capabilities and persistent resource bounds that can make high-fidelity simulations—such as climate and ice-sheet studies—prohibitively expensive. It develops two main directions: machine-learning emulators that preserve solution quality while accelerating computation, and adaptive computational reasoning models that allocate resources across approximation fidelities. In ice-sheet modeling, Gaussian Process emulators with multi-fidelity experimental design reduce costs while maintaining accurate sea-level rise predictions, improving climate-science forecasting for mitigation planning.","Machine Learning for Computational  \nOptimization  \nPierre Thodoroff  \nHughes Hall  \nThis dissertation is submitted on September, 2024 for the degree of Doctor of Philosophy  \nDeclaration  \nThis dissertation 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. It is not substantially the same as any that I have submitted, or am concurrently submitting, for a degree or 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. I further state that no substantial part of my dissertation 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. This dissertation does not exceed the prescribed limit of 60000 words.  \nPierre Thodoroff  \nSeptember, 2024  \nAbstract  \nMachine Learning for Computational Optimization  \nPierre Thodoroff  \nThe exponential growth of computational power has transformed our ability to model and interact with the world, from simulating trillions of atoms in complex molecular dynamics studies to processing billions of financial transactions daily. Despite this progress, computational resources remain fundamentally bounded, creating a critical challenge for applications like climate modeling, where accurate simulations could require orders of magnitude more computing power than currently available. This limitation drives researchers to develop approximations that trade computational cost for solution quality.  \nThis thesis investigates how machine learning algorithms can optimize this cost-quality trade-off in computationally constrained environments. We advance the state of the art through two primary approaches: (1) developing novel machine learning-based emulators that enhance computational efficiency while maintaining solution quality, and (2) creating adaptive computational reasoning models that optimize resource allocation across different approximation fidelities. In ice-sheet modeling—our central case study—we show how Gaussian Process emulators combined with multi-fidelity experimental design can produce accurate sea-level rise predictions while reducing computational costs by up to 70% .  \nBy unifying concepts from computational approximation, resource allocation, and machine learning, this thesis provides a comprehensive framework for understanding and addressing computational constraints in scientific modeling. Our results demonstrate practical pathways to improve climate science predictions, particularly for ice-sheet dynamicsand resulting sea-level rise forecasts, which are critical for developing effective climate change mitigation strategies.  \nAcknowledgements  \nI would like to express my deepest gratitude to my supervisor, Prof. Neil Lawrence, for his continuous support throughout this thesis. Neil is a rare researcher who pushes one to think about fundamental problems across fields, to challenge the status quo, and to create one’s own research path much like an entrepreneur. His relentless pursuit of intellectual curiosity, combined with an eternal optimism, has been the most important trait I’ve learned as a researcher. This journey has given me the confidence to forge my own path and, hopefully, make an impact on the world. I am also thankful for his support of my focus on real-world applications—a key reason I came to Cambridge—which has allowed my thesis to touch on a variety of practical applications.  \nI want to thank my wife, Dr. Maria Vedechkina! You have been my partner through all the ups and downs, the person with whom I can truly share and who understands me and everything we experience. Your continuous support has been the most impactful element leading to the completion","cbCaieeOOFrIlXao","https://ap.wps.com/l/cbCaieeOOFrIlXao","pdf",5985705,1,254,"English","en",105,"# Introduction\n## Thesis outline\n## Publications, contributions and funding\n### Ice-sheet\n### Robotics\n### Schrödinger bridge","[{\"question\":\"Why does computational optimization matter in scientific modeling?\",\"answer\":\"Computational resources are fundamentally bounded, so high-accuracy simulations may require far more computing than is available, forcing approximations that trade cost for solution quality.\"},{\"question\":\"What are the two primary approaches proposed in the thesis?\",\"answer\":\"The thesis advances (1) novel machine learning-based emulators to improve efficiency while maintaining quality, and (2) adaptive computational reasoning models that optimize resource allocation across different approximation fidelities.\"},{\"question\":\"How does the thesis validate its methods in ice-sheet modeling?\",\"answer\":\"Using Gaussian Process emulators combined with multi-fidelity experimental design, the work produces accurate sea-level rise predictions while reducing computational costs by up to 70%.\"}]","Machine Learning for Computational Optimization - Doctor of Philosophy Dissertation | PDF",1785675478,640,{"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},"machine-learning-for-computational-optimization-doctor-of-philosophy-dissertation","",{"@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/machine-learning-for-computational-optimization-doctor-of-philosophy-dissertation/117379/",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],{"name":72,"@type":73,"acceptedAnswer":74},"Why does computational optimization matter in scientific modeling?","Question",{"text":75,"@type":76},"Computational resources are fundamentally bounded, so high-accuracy simulations may require far more computing than is available, forcing approximations that trade cost for solution quality.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the two primary approaches proposed in the thesis?",{"text":80,"@type":76},"The thesis advances (1) novel machine learning-based emulators to improve efficiency while maintaining quality, and (2) adaptive computational reasoning models that optimize resource allocation across different approximation fidelities.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis validate its methods in ice-sheet modeling?",{"text":84,"@type":76},"Using Gaussian Process emulators combined with multi-fidelity experimental design, the work produces accurate sea-level rise predictions while reducing computational costs by up to 70%.","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"]