[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126272-en":3,"doc-seo-126272-105":31,"detail-sidebar-cat-0-en-105":93},{"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},126272,2336475104736,"Quinn","https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222",8,"Research & Report","Enhancing Simulation with Machine Learning and Artificial Intelligence - Dissertation","Stochastic simulation is essential for approximating and analyzing complex uncertain systems, yet classical methods can struggle with high-dimensional information and the need for massive sample counts, limiting timely decisions and effective optimization. This dissertation leverages machine learning and artificial intelligence to improve approximation accuracy and computational efficiency, while also using simulation as a sample-efficient engine to advance AI. It presents two contributions: a neural network–Gaussian process surrogate model and a simulation-optimized procedure for selecting language model prompts to enhance performance.","UC Berkeley  \nUC Berkeley Electronic Theses and Dissertations  \nTitle  \nEnhancing Simulation with Machine Learning and Artificial Intelligence  \nPermalink  \n[https://escholarship.org/uc/item/9rq5m0x9](https://escholarship.org/uc/item/9rq5m0x9)  \nISBN  \n9798288864544  \nAuthor  \nZhang, Haoting  \nPublication Date  \n2025-05-24  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nEnhancing Stochastic Simulation with Machine Learning and Artificial Intelligence  \nBy  \nHaoting Zhang  \nA dissertation submitted in partial satisfaction of the requirements 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:  \nAssociate Professor Zeyu Zheng, Co-Chair  \nProfessor Rhonda Righter, Co-Chair  \nProfessor Zuo-Jun (Max) Shen  \nAssistant Professor Park Sinchaisri  \nSpring 2025  \nEnhancing Stochastic Simulation with Machine Learning and Artificial Intelligence  \nCopyright 2025  \nby  \nHaoting Zhang  \n1  \nAbstract  \nEnhancing Stochastic Simulation with Machine Learning and Artificial Intelligence  \nby  \nHaoting Zhang  \nDoctor of Philosophy in Engineering-Industrial Engineering and Operations Research  \nUniversity of California, Berkeley  \nAssociate Professor Zeyu Zheng, Co-Chair  \nProfessor Rhonda Righter, Co-Chair  \nStochastic simulation serves as a vital tool for approximating and analyzing complex systems under uncertainty across domains such as healthcare, finance, and supply chain management. However, when systems involve high-dimensional information and require large numbers of simulated samples, classical simulation methods may encounter challenges related to model specification and computational complexity. These limitations can impede timely decisionmaking and effective system optimization in today’s data-intensive environments.  \nRecent advances in machine learning (ML) and artificial intelligence (AI) offer promising solutions to these challenges. By capturing highly nonlinear relationships and patterns within stochastic simulation models, ML and AI techniques have the potential to enhance both approximation accuracy and computational efficiency. At the same time, while ML and AI significantly enhance the capabilities of stochastic simulation, simulation methods also contribute to ML and AI by providing cost-effective and sample-efficient techniques—thereby helping democratize access to advanced AI tools.  \nIn line with this mutually beneficial relationship between stochastic simulation and ML/AI, this dissertation introduces: (1) a new surrogate model that integrates neural networks and Gaussian processes to approximate complex stochastic systems; and (2) a simulation optimization procedure that efficiently facilitates language model prompt selection to enhance language model performance.  \ni  \nContents  \nContents i  \nList of Figures iii  \nList of Tables v  \n1 Introduction 1  \n2 Contextual Gaussian Process Bandits with Neural Networks 4  \n2.1 Introduction .................................... 4  \n2.2 Main Procedure .................................. 6  \n2.3 Statistical Properties ............................... 9  \n2.4 Experiments .................................... 13  \n2.5 Conclusion & Impact ............................... 19  \n3 Language Model Prompt Selection via Simulation Optimization 21  \n3.1 Introduction .................................... 21  \n3.2 Problem Description ............................... 26  \n3.3 Search Stage .................................... 30  \n3.4 Evaluation and Selection Stage ......................... 32  \n3.5 Refinement .................................... 42  \n3.6 Experiments .................................... 45  \n3.7 Conclusion ..................................... 53  \n4 Conclusion & Future Work 54  \n4.1 Conclusion ..................................... 54  \n4.2 Future Work ......","cbCaiuXwnXMlqHQr","https://ap.wps.com/l/cbCaiuXwnXMlqHQr","pdf",12718048,7,1,144,"English","en",105,"# 1 Introduction\n# 2 Contextual Gaussian Process Bandits with Neural Networks\n## 2.1 Introduction\n## 2.2 Main Procedure\n## 2.3 Statistical Properties\n## 2.4 Experiments\n## 2.5 Conclusion & Impact\n# 3 Language Model Prompt Selection via Simulation Optimization\n## 3.1 Introduction\n## 3.2 Problem Description\n## 3.3 Search Stage\n## 3.4 Evaluation and Selection Stage\n## 3.5 Refinement\n## 3.6 Experiments\n## 3.7 Conclusion\n# 4 Conclusion & Future Work\n## 4.1 Conclusion\n## 4.2 Future Work","[{\"question\":\"What problem does this dissertation address in stochastic simulation?\",\"answer\":\"It addresses difficulties of classical stochastic simulation when models involve high-dimensional information and require very large numbers of samples, which can hinder timely decision-making and optimization.\"},{\"question\":\"How do machine learning and artificial intelligence improve stochastic simulation?\",\"answer\":\"They learn highly nonlinear relationships and patterns within stochastic simulation models, improving both approximation accuracy and computational efficiency.\"},{\"question\":\"What are the two main contributions proposed in the dissertation?\",\"answer\":\"The dissertation introduces (1) a new surrogate model combining neural networks and Gaussian processes and (2) a simulation optimization procedure that efficiently selects language model prompts to improve language model performance.\"}]","Enhancing Simulation with Machine Learning and Artificial Intelligence - Dissertation | PDF",1785904186,363,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"enhancing-simulation-with-machine-learning-and-artificial-intelligence-dissertation","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"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":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/enhancing-simulation-with-machine-learning-and-artificial-intelligence-dissertation/126272/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does this dissertation address in stochastic simulation?","Question",{"text":77,"@type":78},"It addresses difficulties of classical stochastic simulation when models involve high-dimensional information and require very large numbers of samples, which can hinder timely decision-making and optimization.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How do machine learning and artificial intelligence improve stochastic simulation?",{"text":82,"@type":78},"They learn highly nonlinear relationships and patterns within stochastic simulation models, improving both approximation accuracy and computational efficiency.",{"name":84,"@type":75,"acceptedAnswer":85},"What are the two main contributions proposed in the dissertation?",{"text":86,"@type":78},"The dissertation introduces (1) a new surrogate model combining neural networks and Gaussian processes and (2) a simulation optimization procedure that efficiently selects language model prompts to improve language model performance.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"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":108,"slug":139},19,"General","general"]