[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117044-en":3,"doc-seo-117044-105":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},117044,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Symmetry-invariant quantum machine learning force fields","Machine learning provides efficient yet accurate force fields for atomistic simulations, and recent extensions incorporate quantum computational methods using variational quantum learning models to predict potential energy surfaces and atomic forces from ab initio training data. Limits in trainability and scalability arise from theoretical and practical barriers. Using geometric classical and quantum machine learning inspiration, the work designs symmetry-aware quantum neural networks with physically relevant symmetries as an informed prior. The invariant models outperform generic counterparts and are demonstrated on increasingly complex molecules and a water dimer.","arXiv:2311.11362vI ]quant-ph] 19Nov 2023  \n# Symmetry-invariant quantum machine learning force fields\n\nIsabel Nha Minh Le◎,1,2,*Oriel Kisso,3,4 Julian Schuhmachero,!Ivano Tavernellio,l and Francesco Tacchinool,t  \n¹IBM Quantum,IBM Research Europe-Zurich,8803 Rueschlikon,Suitzerland²Institute for Quantum Information,RWTH Aachen University,52074 Aachen,Germany³European Organization for Nuclear Research(CERN),1211 Geneva,Switzerland⁴Department of Nuclear and Particle Physics,University of Geneva,1211 Geneva,Suitzerland(Dated:November 21,2023)  \nMachine learning techniques are essential tools to compute efficient,yet accurate,force fields foratomistic simulations.This approach has recently been extended to incorporate quantum compu-tational methods,making use of variational quantum learning models to predict potential energysurfaces and atomic forces from ab initio training data.However,the trainability and scalabilityof such models are still limited,due to both theoretical and practical barriers.Inspired by recentdevelopments in geometric classical and quantum machine learning,here we design quantum neuralnetworks that explicitly incorporate,as a data-inspired prior,an extensive set of physically relevantsymmetries.We find that our invariant quantum learning models outperform their more genericcounterparts on individual molecules of growing complexity.Furthermore,we study a water dimeras a minimal example of a system with multiple components,showcasing the versatility of our pro-posed approach and opening the way towards larger simulations.Our results suggest that molecularforce fields generation can significantly profit from leveraging the framework of geometric quantummachine learning,and that chemical systems represent,in fact,an interesting and rich playgroundfor the development and application of advanced quantum machine learning tools.  \n## I.  INTRODUCTION\n\nAtomistic simulations are essential computationaltools for a wide range of research fields such as chemicalphysics,materials science,or biophysics [1-3].Moleculardynamics-one of the most prominent representatives ofthese computer simulation methods-investigates prop-erties of molecular systems by numerically integratingthe mechanical equations of motion for each componentin the system.To this end,accurate knowledge of po-tential energy surfaces and atomic forces is required.Infact,the precision with which these quantities can becomputed critically determines the reliability of the sim-ulation.  \nWhile for medium-sized systems high-accuracy forcescan be obtained with the so-called ab initio methods.such as density functional theory [4,5],their compu-tational cost does not allow for the investigation oflarger systems.In this case,empirically parameterizedforce fields,which are less computationally demandingbut also less precise,are employed [6].Classical ma-chine learning methods have been successfully exploitedto learn the mapping between chemical configurationsand the corresponding atomic forces by handling thetask as a mathematical regression problem,obtaining agood balance between computational efficiency and pre-diction accuracy [7-9].Recently,this philosophy hasbeen extended to the realm of quantum machine learn-ing(QML)[10]by employing variational quantum learn-ing models(VQLMs)based on quantum neural net-works [11,12].This approach gives access to a previ-  \nFigure 1:Overview of the work:we design invariantquantum learning models for a set of relevant molecularsymmetries,obtaining-upon input of simple Cartesiancoordinates-invariant predictions for potential energysurfaces and force fields to be employed in moleculardynamics simulations.  \nously unexplored class of models that are,in principle,particularly well suited to capture genuine quantum me-chanical properties.However,despite some promisingresults on small-scale examples,the applicability of suchQML tools to problems of practical relevance is still lim-ited.In fact,the scalability of VQLMs is often hinderedb","cbCaifcb1OztncI7","https://ap.wps.com/l/cbCaifcb1OztncI7","pdf",1653694,1,12,"English","en",105,"# I. INTRODUCTION\n## Atomistic simulations and force accuracy\n## Ab initio methods vs empirical force fields\n## Classical ML and extension to variational quantum learning\n## Symmetry incorporation via geometric quantum machine learning\n## Reported results and examples","[{\"question\":\"What problem do symmetry-invariant quantum machine learning force fields address?\",\"answer\":\"They aim to learn accurate potential energy surfaces and atomic forces for atomistic simulations while improving the trainability and scalability of quantum machine learning models.\"},{\"question\":\"How do the proposed models incorporate molecular symmetry?\",\"answer\":\"They use quantum neural networks that natively include a physically relevant set of symmetries as a data-inspired prior, following ideas from geometric machine learning.\"},{\"question\":\"Which systems are used to demonstrate the method’s effectiveness?\",\"answer\":\"The approach is evaluated on a single LiH molecule, a single H2O molecule, and a dimer of H2O, showing improvements in trainability and generalization compared with generic quantum models.\"}]","Symmetry-invariant quantum machine learning force fields | PDF",1785673336,30,{"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},"symmetry-invariant-quantum-machine-learning-force-fields","",{"@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/symmetry-invariant-quantum-machine-learning-force-fields/117044/",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","2026-08-02",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},"What problem do symmetry-invariant quantum machine learning force fields address?","Question",{"text":75,"@type":76},"They aim to learn accurate potential energy surfaces and atomic forces for atomistic simulations while improving the trainability and scalability of quantum machine learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the proposed models incorporate molecular symmetry?",{"text":80,"@type":76},"They use quantum neural networks that natively include a physically relevant set of symmetries as a data-inspired prior, following ideas from geometric machine learning.",{"name":82,"@type":73,"acceptedAnswer":83},"Which systems are used to demonstrate the method’s effectiveness?",{"text":84,"@type":76},"The approach is evaluated on a single LiH molecule, a single H2O molecule, and a dimer of H2O, showing improvements in trainability and generalization compared with generic quantum models.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]