[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122648-en":3,"doc-seo-122648-105":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},122648,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Improving Quantum Circuit Synthesis with Machine Learning","Noisy Intermediate Scale Quantum（NISQ）阶段中，寻找能最小化昂贵且易出错的多比特门数量的量子算法实现至关重要。本文研究幺正综合（unitary synthesis）：在给定目标幺正矩阵时构造量子电路的最优解，然而现有自底向上的综合方法因运行时间呈指数增长而受限。作者提出QSeed：利用机器学习对幺正数据集进行学习，用推断快速给出资源高效电路模板，并在64量子比特的模指数电路上相较现有技术实现约3.7倍加速，同时门数保持较低；性能也可泛化到训练中未见的电路家族。","Improving Quantum Circuit Synthesis with  \nMachine Learning  \nMathias Weiden 1 , Ed Younis2 , Justin Kalloor 1 , John Kubiatowicz 1 , and Costin Iancu2  \n1Department of Electrical Engineering and Computer Science, University of California, Berkeley {mtweiden, jkalloor3, [kubitron](kubitron}@cs.berkeley.edu)[}](kubitron}@cs.berkeley.edu)[@cs.berkeley.edu](kubitron}@cs.berkeley.edu)  \n2 Computational Research Division, Lawrence Berkeley National Laboratory  \n{edyounis, [cciancu](cciancu}@lbl.gov)[}](cciancu}@lbl.gov)[@lbl.gov](cciancu}@lbl.gov)  \narXiv :2306 .05622v1 [ quant-ph] 9 Jun 2023  \nAbstract—In the Noisy Intermediate Scale Quantum (NISQ) era, finding implementations of quantum algorithms that minimize the number of expensive and error prone multi-qubit gates is vital to ensure computations produce meaningful outputs. Unitary synthesis, the process of finding a quantum circuit that implements some target unitary matrix, is able to solve this problem optimally in many cases. However, current bottom-up unitary synthesis algorithms are limited by their exponentially growing run times. We show how applying machine learning to unitary datasets permits drastic speedups for synthesis algorithms. This paper presents QSeed, a seeded synthesis algorithm that employs a learned model to quickly propose resource efficient circuit implementations of unitaries. QSeed maintains low gate countsand offers a speedup of 3.7 × in synthesis time over the state of the art for a 64 qubit modular exponentiation circuit, a core component in Shor’s factoring algorithm. QSeed’s performance improvements also generalize to families of circuits not seen during the training process.  \nI. INTRODUCTION  \nQuantum computers are capable of solving many problems that are thought to be intractable on classical computers [17] . In the Noisy Intermediate Scale Quantum (NISQ) [21] era, where full error correction is not yet realizable, careful consideration of error mitigation techniques in compilation are vitally important. To this end, techniques such as random compilation [30], noise-adaptive mapping [16], [28], and zero noise extrapolation [6] have been proposed. Google’s quantum supremacy experiments demonstrated empirically that simply reducing the number of operations remains an impactful noise mitigation strategy [2] . The need for optimization algorithms that reduce gate counts is therefore critical.  \nRule based circuit optimization algorithms are widely used because they are quick and effective for small circuits [1], [9],[13], [20] . These techniques rely on recognizing small gate patterns and replacing them with more efficient implementations, and by making small, heuristic-guided transformations. Recently, deep Reinforcement Learning has emerged as a technique to automate the discovery and application of circuit transformation rules [5], [18],[23] . However, these techniques remain hindered by a narrow, local view of the circuits they optimize or by the limitations of human intuited heuristics.  \nUnitary synthesis is a bottom-up method for constructing circuit implementations of unitary matrices. It has become popular as an optimization technique as it eschews a gate  \nlevel view of the program for a more global perspective. This broader frame of reference allows for optimization that is otherwise impossible with rule based methods. State-ofthe-art synthesis algorithms have demonstrated that they are capable of producing the best known implementations of a variety of circuits [3], [27], [35] . Synthesis searches over a tree of increasingly more complex candidate circuits and evaluates each one’s ability to implement a unitary target. Yet, these techniques remain limited in their applicability due to their exponentially growing run times. Circuits wider than five qubits must be partitioned into smaller subcircuits, which can each be individually synthesized. Importantly, even in these cases, where synthesis is not given a full global view of the cir","cbCaidCMaSElECPY","https://ap.wps.com/l/cbCaidCMaSElECPY","pdf",1635278,1,11,"English","en",105,"# Introduction\n## NISQ与门计数优化需求\n## 规则式优化与强化学习的局限\n## 幺正综合：全局视角与指数时间瓶颈\n# Background\n## Unitary synthesis与可参数化量子电路","[{\"question\":\"为什么NISQ时代需要减少昂贵且易出错的多比特门数量？\",\"answer\":\"在无法实现完整纠错的NISQ阶段，门操作带来的误差会显著影响计算结果，因此优化编译时需尽量降低多比特门的数量以提升输出可信度。\"},{\"question\":\"本文提出的QSeed如何利用机器学习加速幺正综合？\",\"answer\":\"QSeed使用学习得到的模型来快速提出资源高效的电路模板，用ML推断替代昂贵的综合搜索树，从而更快直接实现目标幺正矩阵。\"},{\"question\":\"QSeed的性能提升能否泛化到训练数据之外？\",\"answer\":\"能。文中指出QSeed不仅对训练中见过的电路族有效，也能推广到训练过程中未出现的电路家族，并保持加速与较低门数的优势。\"}]","Improving Quantum Circuit Synthesis with Machine Learning | PDF",1785811931,28,{"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},"improving-quantum-circuit-synthesis-with-machine-learning","",{"@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/improving-quantum-circuit-synthesis-with-machine-learning/122648/",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","2026-08-04",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},"为什么NISQ时代需要减少昂贵且易出错的多比特门数量？","Question",{"text":75,"@type":76},"在无法实现完整纠错的NISQ阶段，门操作带来的误差会显著影响计算结果，因此优化编译时需尽量降低多比特门的数量以提升输出可信度。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"本文提出的QSeed如何利用机器学习加速幺正综合？",{"text":80,"@type":76},"QSeed使用学习得到的模型来快速提出资源高效的电路模板，用ML推断替代昂贵的综合搜索树，从而更快直接实现目标幺正矩阵。",{"name":82,"@type":73,"acceptedAnswer":83},"QSeed的性能提升能否泛化到训练数据之外？",{"text":84,"@type":76},"能。文中指出QSeed不仅对训练中见过的电路族有效，也能推广到训练过程中未出现的电路家族，并保持加速与较低门数的优势。","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"]