[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125840-en":3,"doc-seo-125840-105":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},125840,1099523885074,"Ivy","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Machine learning force-field models for metallic spin glass","Metallic spin-glass systems feature randomly distributed local moments coupled by long-range, electron-mediated effective interactions, producing frustrated magnetism and collective freezing at low temperatures. The work presents a scalable machine-learning framework for dynamical simulations, using a locality-based Behler-Parrinello neural network to predict electron-induced local magnetic fields that govern spin dynamics. A symmetry-invariant, atom-centered magnetic descriptor incorporates spin degrees of freedom, enabling accurate force-field representations. The approach is applied to relaxation dynamics in an amorphous generalization of the s-d model, highlighting potential for large-scale itinerant magnets with quenched disorder.","Machine learning force-field models for metallic spin glass  \narXiv :2311 . 16964v1 [ cond-mat .dis-nn] 28 Nov 2023  \nMenglin Shi, 1 Sheng Zhang, 1 and Gia-Wei Chern 1  \n1 Department of Physics, University of Virginia, Charlottesville, VA 22904, USA  \n(Dated: November 29, 2023)  \nMetallic spin glass systems, such as dilute magnetic alloys, are characterized by randomly distributed local moments coupled to each other through a long-range electron-mediated effective interaction. We present a scalable machine learning (ML) framework for dynamical simulations of metallic spin glasses. A Behler-Parrinello type neural-network model, based on the principle of locality, is developed to accurately and efficiently predict electron-induced local magnetic fields that drive the spin dynamics. A crucial component of the ML model is a proper symmetry-invariant representation of local magnetic environment which is direct input to the neural net. We develop such a magnetic descriptor by incorporating the spin degrees of freedom into the atom-centered symmetry function methods which are widely used in ML force-field models for quantum molecular dynamics. We apply our approach to study the relaxation dynamics of an amorphous generalization of the s-d model. Our work highlights the promising potential of ML models for large-scale dynamical modeling of itinerant magnets with quenched disorder.  \nI. INTRODUCTION  \nSpin glasses are disordered magnetic materials in which interactions between localized magnetic moments are frustrated due to quenched disorder [1–4] . As a result of the frustrated interactions, no conventional long-range magnetic order, such as the ferromagnetic or N´eel states, can be established. Yet spin glass systems exhibit collective freezing transitions below a characteristic temperature Tf , indicating new magnetic states of matter at low temperatures. The term “glass” comes from the analogy between the disordered spins in a low-temperature spin-glass phase and the atomic positional disorder of a structural glass [5, 6] . It is worth noting that, whereas a frozen disordered atomic configuration arises spontaneously from the exponentially slow relaxation of a supercooled liquid, quenched randomness plays a central role in spin glass systems.  \nSeveral theoretical models have been introduced to understand the nature of spin-glass phases and transitions. A canonical example is the Edwards-Anderson model [7] which describes random exchange interactions between nearest-neighbor Ising spins σi on a lattice: H = −P⟨ij⟩ Jij σi σj . The coupling coefficients are random variables with equal probability of being positive (ferromagnetic) or negative (antiferromagnetic) . Meanfield theories of spin glasses, such as the SherringtonKirkpatrick model [8], further shed light on the nature of spin-glass “order”, which later led to the idea of replica symmetry breaking and related order parameters for spin-glass phases [9–12] . The physical insight and mathematical techniques developed in the study of spin glass have found applications in disciplines as diverse as computer science, biology, and economics [13–15] .  \nExperimentally, the prototype spin-glass materials are dilute magnetic alloys, where a small amount of magnetic impurity, such as Fe or Mn, are randomly substituted into the lattice of a nonmagnetic metallic host (e.g. Ag, Cu, Pt) [2–4, 16 , 17] . They are prepared by rapidly cool-  \ning the liquid alloy, thus fixing the strongly interacting particles at random positions within the resulting solid. As these magnetic impurities are typically several lattice constants away from each other, their effective interactions are mediated by conducting electrons from the metallic host. Due to the itinerant nature of conducting electrons, the resultant effective spin-spin interactions are usually long-ranged, as exemplified the by wellknown Ruderman-Kittel-Kazuya-Yosida (RKKY) interactions [18–20] . The RKKY interaction also oscillates between fe","cbCaidbvOqe5gK6i","https://ap.wps.com/l/cbCaidbvOqe5gK6i","pdf",4327261,7,1,12,"English","en",105,"# Introduction\n## Spin-glass background and models\n## Dilute magnetic alloys and electron-mediated interactions\n## Challenge of dynamical simulation of itinerant magnets\n## Proposed ML framework for scalable spin-glass dynamics","[{\"question\":\"What problem does the paper address in modeling metallic spin glasses?\",\"answer\":\"Full dynamical simulations require repeatedly solving electron Hamiltonians to obtain electron-driven fields, which is computationally prohibitive for large disordered systems.\"},{\"question\":\"How does the proposed machine learning model predict spin dynamics?\",\"answer\":\"It uses a locality-based Behler-Parrinello type neural network to predict electron-induced local magnetic fields, which then drive the spin dynamics.\"},{\"question\":\"What is the role of the magnetic descriptor in the ML framework?\",\"answer\":\"The model relies on a symmetry-invariant representation of the local magnetic environment, built by extending atom-centered symmetry-function methods to include spin degrees of freedom.\"}]","Machine learning force-field models for metallic spin glass | PDF",1785901514,30,{"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},"machine-learning-force-field-models-for-metallic-spin-glass","",{"@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/machine-learning-force-field-models-for-metallic-spin-glass/125840/",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 the paper address in modeling metallic spin glasses?","Question",{"text":77,"@type":78},"Full dynamical simulations require repeatedly solving electron Hamiltonians to obtain electron-driven fields, which is computationally prohibitive for large disordered systems.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does the proposed machine learning model predict spin dynamics?",{"text":82,"@type":78},"It uses a locality-based Behler-Parrinello type neural network to predict electron-induced local magnetic fields, which then drive the spin dynamics.",{"name":84,"@type":75,"acceptedAnswer":85},"What is the role of the magnetic descriptor in the ML framework?",{"text":86,"@type":78},"The model relies on a symmetry-invariant representation of the local magnetic environment, built by extending atom-centered symmetry-function methods to include spin degrees of freedom.","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},[95,99,103,107,112,117,121,123,128,131,135],{"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":30,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]