[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127150-en":3,"doc-seo-127150-105":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},127150,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Designing Efficient, Interpretable, and Generalizable Machine Learning Interatomic Potentials - Dissertation","Interatomic potentials enable faster atomic-scale simulations than first-principles methods but have faced a shift toward data-driven ML approaches that can increase complexity and reduce generalizability. This dissertation addresses the classical-versus-ML false dichotomy by pursuing improved speed, interpretability, and generalizability. It benchmarks a classical spline-based MEAM against MLIPs, showing near-DFT accuracy with strong accuracy-speed tradeoffs, then introduces a splinebased neural network potential (s-NNP). Finally, it proposes a loss-landscape entropy metric to predict out-of-domain performance and data efficiency, analyzing impacts on MD stability and model design.","© 2023 Joshua Alexander Vita  \nDESIGNING EFFICIENT, INTERPRETABLE, AND GENERALIZABLE MACHINE  \nLEARNING INTERATOMIC POTENTIALS  \nBY  \nJOSHUA ALEXANDER VITA  \nDISSERTATION  \nSubmitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Materials Science and Engineering  \nin the Graduate College of the  \nUniversity of Illinois Urbana-Champaign, 2023  \nUrbana, Illinois  \nDoctoral Committee:  \nProfessor Dallas Trinkle  \nProfessor Pascal Bellon  \nProfessor Ellad Tadmor, University of Minnesota  \nAssociate Professor Andr´e Schleife  \nABSTRACT  \nInteratomic potentials (IPs) are invaluable tools in the fields of computational materials science and chemistry for their ability to accelerate atomic-scale simulations beyond the length-and time-scales that are accessible using first-principles techniques. In recent years, the application of machine learning (ML) and deep learning (DL) models and algorithms towards IP development has been a major area of interest, where machine learning interatomic potentials (MLIPs) are seen as being more flexible and accurate than their classical potential counterparts. The resounding success of MLIPs has led to a major shift away from the physical foundations characteristic of classical models, and towards more data-driven methods. While a data-centric fitting approach guided by error-based training metrics can be expected to correlate well with accuracies on higher-level property predictions, it has also resulted in a pattern of developing slower, more complex, and less general models. This work aims to address these issues by rectifying the false dichotomy between classical and ML IPs, and developing models and techniques that show how IP design can be improved with a focus on speed, interpretability, and generalizability.  \nBy first performing an in-depth comparison of the performance of a classical spline-based MEAM (sMEAM) IP relative to a collection of MLIPs, I demonstrate the competitive nature of s-MEAM on a variety of common benchmarking tests. s-MEAM is shown to be capable of achieving errors comparable to those of the benchmarked MLIPs while maintaining its high speeds and interpretability, establishing its position on the accuracy-speed pareto front. These results demonstrate that high model complexities may not be strictly necessary in order to achieve near-DFT accuracy for certain benchmarking tasks and suggest an alternative route towards sampling the high accuracy, low complexity region of model space by starting with forms that promote simpler and more interpretable interatomic potentials  \nI then build upon these results by leveraging the strengths of both s-MEAM and modern neural network (NN) architectures to propose a novel MLIP framework. The proposed framework, which I call the splinebased neural network potential (s-NNP), is a simplified version of the traditional NNP that can be used to describe complex datasets in a computationally efficient manner. I demonstrate how this framework can be used to probe the boundary between classical and ML IPs, highlighting the benefits of key architectural changes for improving model accuracy and interpretability.  \nFinally, I present a metric using the entropy of the loss landscape, and show how it can be used to predict model performance on out-of-domain data and provide insights regarding model design and optimization. Using this metric, I demonstrate how architectural and optimization choices influence the generalization capacity of neural network (NN) IPs, revealing trends in molecular dynamics (MD) stability, data efficiency, and loss landscapes. With a large-scale study on two state-of-the-art MLIPs, and their optimizers, I show that the metric of loss entropy predicts out-of-distribution error and data efficiency despite being computed only on the training set.  \nTo the people who taught me to explore, be curious, and have fun  \niii  \nACKNOWLEDGMENTS  \nI learned very early in life that my experiences, emo","cbCainkVAFi13nU5","https://ap.wps.com/l/cbCainkVAFi13nU5","pdf",8328576,1,120,"English","en",105,"# Abstract\n## Motivation and problem framing\n## Benchmarking s-MEAM vs MLIPs\n## Proposed splinebased neural network potential (s-NNP)\n## Loss-landscape entropy metric and generalization analysis","[{\"question\":\"Why are interatomic potentials important in computational materials science?\",\"answer\":\"They accelerate atomic-scale simulations beyond the length and time scales accessible with first-principles techniques, enabling practical studies of materials and chemical systems.\"},{\"question\":\"What is the main issue addressed with current ML-based interatomic potentials?\",\"answer\":\"ML approaches can move away from classical physical foundations toward data-driven fitting, sometimes producing slower, more complex, and less general models.\"},{\"question\":\"How does the dissertation evaluate or predict model performance outside the training domain?\",\"answer\":\"It introduces a metric based on the entropy of the loss landscape, showing it can predict out-of-distribution error and data efficiency using only training-set information.\"}]","Designing Efficient, Interpretable, and Generalizable Machine Learning Interatomic Potentials - Dissertation | PDF",1785937206,302,{"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},"designing-efficient-interpretable-and-generalizable-machine-learning-interatomic-potentials-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/designing-efficient-interpretable-and-generalizable-machine-learning-interatomic-potentials-dissertation/127150/",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","2026-08-05",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},"Why are interatomic potentials important in computational materials science?","Question",{"text":75,"@type":76},"They accelerate atomic-scale simulations beyond the length and time scales accessible with first-principles techniques, enabling practical studies of materials and chemical systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main issue addressed with current ML-based interatomic potentials?",{"text":80,"@type":76},"ML approaches can move away from classical physical foundations toward data-driven fitting, sometimes producing slower, more complex, and less general models.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the dissertation evaluate or predict model performance outside the training domain?",{"text":84,"@type":76},"It introduces a metric based on the entropy of the loss landscape, showing it can predict out-of-distribution error and data efficiency using only training-set information.","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"]