[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119559-en":3,"doc-seo-119559-105":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":20,"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},119559,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Classical Simulability and Trainability of Quantum Machine Learning - Doctoral Dissertation","Variational Quantum Algorithms (VQA) enable quantum machine learning and optimization by using parameterized quantum circuits to estimate functions that are costly for classical computers, while optimizing parameters via classical procedures such as gradient descent. Near-term limitations on available quantum hardware make it crucial to reduce quantum device calls, especially under trainability issues like barren plateaus and sample-complexity growth. This thesis develops new algorithms and theory to improve VQA efficiency, including ALSO for shallow alternating layered circuits and Ansatz Independent Shadow Optimization using shadow tomography, with provable and experimentally supported exponential savings.","Classical Simulability and Trainability of Quantum Machine  \nLearning  \nby  \nAfrad Muhamed Basheer  \nA dissertation submitted in fulfillment of the requirements for the degree of Doctor of Philosophy  \nUniversity of Technology Sydney 2024  \ni  \nCertificate of Original Authorship  \nI, Afrad Muhamed Basheer, declare that this thesis is submitted in fulfilment of the requirements for the award of Doctor of Philosophy, in the Faculty of Engineering and Information Technology at the University of Technology Sydney.  \nThis thesis is wholly my own work unless otherwise referenced or acknowledged. In addition, I certify that all information sources and literature used are indicated in the thesis.  \nThis document has not been submitted for qualifications at any other academic institution. This research is supported by the Australian Government Research Training Program.  \nProduction Note:  \nSignature removed prior to publication.  \nAfrad Muhamed Basheer 24-09-2024  \nii  \nAcknowledgements  \nI would like to express my deepest gratitude to my supervisors, Prof. Yuan Feng and Prof. Sanjiang Li, for their invaluable guidance, support, and encouragement throughout my PhD journey. Their expertise and insights have been instrumental in shaping my research and bringing this thesis to fruition. I am also grateful to Distinguished Prof. Mingsheng Ying, who stepped in as my co-supervisor towards the end of my PhD, providing essential support and guidance during a crucial phase of my research.  \nFinancially, my research was primarily supported by my supervisors’ Australian Research Council research grant. I was also supported by the University of Technology Sydney (UTS) International Research Scholarship and the Sydney Quantum Academy (SQA) supplementary scholarship, which provided additional funding and resources.  \nI am profoundly thankful to A/Prof. Christopher Ferrie, who has been a co-author on all the papers included in this thesis, and has supported me in numerous ways beyond our collaborations. His mentorship and generous contributions have significantly enriched my academic experience.  \nI would also like to extend my heartfelt thanks to my childhood friend Afham, who also embarked on a PhD journey in the same field at the same university. His academic and non-academic support has been invaluable, and I am grateful for the many ways he has helped me throughout this journey.  \nA special thank you goes to Dr. Hakop Pashayan for his guidance and collaboration during my PhD, including co-authoring one of my papers. His advice and support at critical moments have been greatly appreciated.  \nI would like to thank Christian Bertoni, Guangxi Li, and Dr. Richard Kueng for their help with academic discussions which have been immensely beneficial to my work.  \nI also wish to acknowledge the administrative staff of UTS and SQA, who provided assistance at various stages of my PhD. Their support has been instrumental in navigating the many logistical aspects of my research journey.  \nDuring my PhD, I had the pleasure of collaborating with Dr. Eric Howard, Prof. Gavin Brennen, and Christopher Tam from BTQ, which greatly expanded my perspectives in quantum computing. I am especially grateful for the opportunity to work with Dr. Eric Howard and Iftekher Chowdhury on experimental physics projects, even though these works are not part of my thesis.  \nFinally, I would like to acknowledge all my friends, family, and colleagues who have supported me throughout this journey. While I choose not to name individuals to bind the space complexity of this section and avoid the risk of leaving anyone out, I deeply appreciate their encouragement and for being with me every step of the way.  \niii  \nAbstract  \nVariational Quantum Algorithms (VQA) form an important class of quantum machine learning and optimization algorithms, with potential applications in supervised learning, combinatorial optimization, chemical simulation, dimensionality reduction, etc. At its core, it ","cbCaiskR0U4uTaMe","https://ap.wps.com/l/cbCaiskR0U4uTaMe","pdf",6352998,1,188,"English","en",105,"# Abstract\n# Acknowledgements\n# Certificate of Original Authorship\n# Introduction to Variational Quantum Algorithms\n## Trainability and Sample Complexity Challenges\n## Proposed Training Algorithms and Theoretical Results","[{\"question\":\"What problem does the thesis focus on in variational quantum algorithms?\",\"answer\":\"The thesis targets the increased quantum resource demands caused by trainability issues (e.g., barren plateaus) and sample complexity problems in near-term VQAs.\"},{\"question\":\"What is Alternating Layered Shadow Optimization (ALSO)?\",\"answer\":\"ALSO is a training algorithm for shallow alternating layered VQAs that uses classical shadows of quantum input data to reduce the quantum resources required for training, with efficient classical optimization and performance guarantees.\"},{\"question\":\"How does Ansatz Independent Shadow Optimization extend shadow tomography for VQAs?\",\"answer\":\"It broadens the applicability of shadow tomography to a wide range of shallow ansatzes and low Frobenius norm observables, demonstrating exponential savings in quantum resources beyond the original setting.\"}]","Classical Simulability and Trainability of Quantum Machine Learning - Doctoral Dissertation | PDF",1785724966,474,{"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},"classical-simulability-and-trainability-of-quantum-machine-learning-doctoral-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/classical-simulability-and-trainability-of-quantum-machine-learning-doctoral-dissertation/119559/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis focus on in variational quantum algorithms?","Question",{"text":75,"@type":76},"The thesis targets the increased quantum resource demands caused by trainability issues (e.g., barren plateaus) and sample complexity problems in near-term VQAs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is Alternating Layered Shadow Optimization (ALSO)?",{"text":80,"@type":76},"ALSO is a training algorithm for shallow alternating layered VQAs that uses classical shadows of quantum input data to reduce the quantum resources required for training, with efficient classical optimization and performance guarantees.",{"name":82,"@type":73,"acceptedAnswer":83},"How does Ansatz Independent Shadow Optimization extend shadow tomography for VQAs?",{"text":84,"@type":76},"It broadens the applicability of shadow tomography to a wide range of shallow ansatzes and low Frobenius norm observables, demonstrating exponential savings in quantum resources beyond the original setting.","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"]