[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127371-en":3,"doc-seo-127371-105":30,"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":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},127371,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine learning supported annealing for prediction of grand canonical crystal structures","This study investigates the use of Factorization Machines with Quantum Annealing (FMQA) to tackle the crystal structure problem (CSP) in materials science. FMQA is framed as a black-box optimization method that integrates machine learning with annealing machines to generate samples minimizing a prescribed loss. The loss is set to the energy of crystal configurations computed from a predefined interatomic potential, enabling efficient sampling of favorable structures. The work also assesses whether the algorithm learns energies of metastable local minima and finds potential ground-state samples and recovers relational order among minima.","arXiv :2408 .03556v1 [ cond-mat .mtrl-sci ] 7 Aug 2024  \nMachine learning supported annealing for prediction of grand canonical crystal  \nstructures  \nYannick Couzini´e, 1, 2, ∗ Yuya Seki,3, 4 Yusuke Nishiya , 1, 2 Hirofumi Nishi, 1, 2 Taichi Kosugi, 1, 2 Shu Tanaka,4, 5, 6, 7 and Yu-ichiro Matsushita1, 2, 8  \n1 Department of Physics, The University of Tokyo Hongo, Bunkyo-ku, Tokyo, Japan.  \n2 Quemix Inc. , Taiyo Life Nihombashi Building, 2-11-2, Nihombashi Chuo-ku, Tokyo, Japan  \n3 Graduate School of Science and Technology, Keio University,  \n3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, Japan  \n4 Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC),  \nKeio University, 2-15-45 Mita, Minato-ku, Tokyo, Japan  \n5 Department of Applied Physics and Physico-Informatics, Keio University,  \n3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, Japan  \n6 Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q),  \nKeio University, 2-15-45 Mita, Minato-ku, Tokyo,  \n7 Green Computing Systems Research Organization (GCS),  \nWaseda University, 162-0042 Wasedamachi, Shinjuku-ku, Tokyo, Japan  \n8 Quantum Material and Applications Research Center,  \nNational Institutes for Quantum Science and Technology (QST), 2-12-1, Ookayama, Meguro-ku, Tokyo, Japan  \n(Dated: August 8, 2024)  \nThis study investigates the application of Factorization Machines with Quantum Annealing (FMQA) to address the crystal structure problem (CSP) in materials science. FMQA is a black-box optimization algorithm that combines machine learning with annealing machines to find samples to a black-box function that minimize a given loss. The CSP involves determining the optimal arrangement of atoms in a material based on its chemical composition, a critical challenge in materials science. We explore FMQA’s ability to efficiently sample optimal crystal configurations by setting the loss function to the energy of the crystal configuration as given by a predefined interatomic potential. Further we investigate how well the energies of the various metastable configurations, or local minima of the potential, are learned by the algorithm. Our investigation reveals FMQA’s potential in quick ground state sampling and in recovering relational order between local minima.  \nI. INTRODUCTION  \nSolving the crystal structure problem (CSP) from chemical composition remains an enduring challenge in materials science, demanding innovative methodologies to overcome the exponential growth of potential structures as the system size increases [1] . Various approaches on classical computers have been developed [2], e.g. random search [3–6], simulated annealing (SA) [7–9], minima hopping [10, 11], evolutionary algorithms [12–15] and particle swarm optimization [16, 17] . Various software suites such as USPEX [18, 19], CALYPSO [16, 20 , 21], and CrySPY [22] are used in standard approaches to the CSP. Being on classical hardware, these algorithms do not manage to compute large scale structures. With the continually increasing computational capacity of quantum computers, there is a need to develop efficient algorithms to solve the CSP that is compatible with quantum hardware.  \nIn recent years, the use of quantum computers has attracted a great deal of attention as a means of searching for globally optimal solutions [23–29] . Quantum computers are characterized by their ability to escape from  \n∗ [couzinie.y.aa@m.titech.ac.jp](couzinie.y.aa@m.titech.ac.jp)  \nlocally stable solutions and accelerate the search for globally optimal solutions by utilizing the quantum tunneling effect [26, 30] and the superposition of states to concurrently evaluate a large state space [31] . Quantum annealing (QA) machines [23, 32–35] and gate-based quantum computers [31] are the two main current architecturesin development. Exhaustive structure search schemes using gate-based quantum computers [36–38], quantum annealers and the equivalent Ising machines [39–43] have recently been proposed.  \nUsing the en","cbCaiu06As0X29vG","https://ap.wps.com/l/cbCaiu06As0X29vG","pdf",1395931,1,9,"English","en",105,"# Introduction\n## Classical approaches to CSP\n## Quantum-computing motivations and architectures\n## QUBO/HUBO encodings and hardware limitations","[{\"question\":\"What does FMQA combine to solve the crystal structure problem?\",\"answer\":\"FMQA combines Factorization Machines (machine learning) with quantum annealing to perform black-box optimization for crystal structure sampling.\"},{\"question\":\"How is the FMQA loss function defined in this study?\",\"answer\":\"The loss function is defined as the energy of a crystal configuration evaluated using a predefined interatomic potential.\"},{\"question\":\"What does the study evaluate regarding metastable structures?\",\"answer\":\"It examines how well FMQA learns the energies of metastable configurations, interpreted as local minima of the potential, and whether it can recover relational order between them.\"}]","Machine learning supported annealing for prediction of grand canonical crystal structures | PDF",1785938547,23,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-supported-annealing-for-prediction-of-grand-canonical-crystal-structures","",{"@graph":36,"@context":86},[37,54,69],{"@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-supported-annealing-for-prediction-of-grand-canonical-crystal-structures/127371/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",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 does FMQA combine to solve the crystal structure problem?","Question",{"text":76,"@type":77},"FMQA combines Factorization Machines (machine learning) with quantum annealing to perform black-box optimization for crystal structure sampling.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the FMQA loss function defined in this study?",{"text":81,"@type":77},"The loss function is defined as the energy of a crystal configuration evaluated using a predefined interatomic potential.",{"name":83,"@type":74,"acceptedAnswer":84},"What does the study evaluate regarding metastable structures?",{"text":85,"@type":77},"It examines how well FMQA learns the energies of metastable configurations, interpreted as local minima of the potential, and whether it can recover relational order between them.","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":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},"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":107,"slug":138},19,"General","general"]