[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117015-en":3,"doc-seo-117015-105":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},117015,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning for Practical Quantum Error Mitigation","Quantum computers promise major advantages, yet quantum errors remain the dominant barrier on near-term hardware. Quantum error mitigation (QEM) can improve accuracy but introduces additional runtime cost. This work uses experiments on state-of-the-art quantum processors with up to 100 qubits to show that machine learning for quantum error mitigation (ML-QEM) can drastically reduce mitigation cost without sacrificing accuracy. Linear regression, random forests, multilayer perceptrons, and graph neural networks are benchmarked across diverse circuit classes and device-noise profiles, validated via zero-noise extrapolation references and extended with a scalable approach for improved runtime efficiency.","arXiv :2309 . 17368v2 [ quant-ph] 22 Nov 2024  \nMachine Learning for Practical Quantum Error Mitigation  \nHaoran Liao, 1, 2, ∗ Derek S. Wang, 1, ∗ Iskandar Sitdikov, 1 Ciro Salcedo, 1 Alireza Seif, 1 and Zlatko K. Minev 1,†  \n1 IBM Quantum, IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA  \n2 Department of Physics, University of California, Berkeley, CA 94720, USA  \nQuantum computers progress toward outperforming classical supercomputers, but quantum errors remain their primary obstacle. The key to overcoming errors on near-term devices has emerged through the field of quantum error mitigation, enabling improved accuracy at the cost of additional run time. Here, through experiments on state-of-the-art quantum computers using up to 100 qubits, we demonstrate that without sacrificing accuracy machine learning for quantum error mitigation (ML-QEM) drastically reduces the cost of mitigation. We benchmark ML-QEM using a variety of machine learning models—linear regression, random forests, multi-layer perceptrons, and graph neural networks—on diverse classes of quantum circuits, over increasingly complex device-noise profiles, under interpolation and extrapolation, and in both numerics and experiments. These tests employ the popular digital zero-noise extrapolation method as an added reference. Finally, we propose a path toward scalable mitigation by using ML-QEM to mimic traditional mitigation methods with superior runtime efficiency. Our results show that classical machine learning can extend the reach and practicality of quantum error mitigation by reducing its overheads and highlight its broader potential for practical quantum computations.  \nI. INTRODUCTION  \nQuantum computers hold the promise of substantial advantages over their classical counterparts, with speedups ranging from polynomial to exponential [1, 2] . However, realizing these advantages in practice is hindered by unavoidable errors in the physical quantum devices. Achieving reduced error rates and increasing qubit numbers will in principle ultimately allow fault-tolerant quantum error correction to overcome these errors [3] . While this goal remains out of reach, quantum error mitigation (QEM) strategies have been developed to harness imperfect quantum computers to produce near noise-free results despite the presence of unmonitored errors [2, 4– 9] . These strategies are not just a temporary fix, but are an essential step towards achieving near-term quantum utility and establishing a path to outperform classical supercomputers [2, 9] .  \nThe main challenge to employing QEM in practice lies in devising schemes that yield accurate results without excessive runtime overheads. For context, quantum error correction relies on overheads in qubit counts and real-time monitoring to eliminate errors in each run of a circuit. In contrast, QEM obviates the need for these overheads but at the cost of increased algorithmic runtime. Instead, QEM produces an estimator for the noisefree expectation values of a target circuit by employing an ensemble of many noisy quantum circuits. For example, in the cornerstone QEM approach known as zeronoise extrapolation (ZNE) [10–12], an input circuit is recompiled into multiple circuits that are logically equivalent but each with an increased expected number of errors. By analyzing the dependence of the measured  \n∗ These authors contributed equally  \n† [haoran.liao@berkeley.edu](haoran.liao@berkeley.edu)[ ](haoran.liao@berkeley.edu)[zlatko.minev@ibm.com](zlatko.minev@ibm.com)  \nexpectation values for each noisy circuit, one can estimate the ‘zero-noise’, ideal expectation value of the original circuit. While ZNE does not yield an unbiased estimator, other QEM methods, such as probabilistic error cancellation (PEC) [7, 10 , 11] come fortified with rigorous theoretical guarantees and sampling complexity bounds. Unfortunately, it is believed that QEM methods demand exponential sampling overheads for arbitrarily high accuracies[1","cbCaiv5m4q7xGAVh","https://ap.wps.com/l/cbCaiv5m4q7xGAVh","pdf",1197218,1,22,"English","en",105,"# Introduction\n## Quantum error mitigation and runtime overhead\n## Zero-noise extrapolation and other QEM methods\n## Motivation for ML-QEM","[{\"question\":\"What problem does ML-QEM aim to solve in practical quantum computing?\",\"answer\":\"ML-QEM targets the core practical challenge of achieving accurate quantum error mitigation without excessive runtime overhead from additional mitigation circuits.\"},{\"question\":\"How is ML-QEM evaluated in the study?\",\"answer\":\"The work benchmarks multiple machine learning models on diverse quantum circuit classes across increasingly complex device-noise profiles, using both interpolation and extrapolation and comparing against a reference digital zero-noise extrapolation method.\"},{\"question\":\"What approach does the paper propose for scalable quantum error mitigation?\",\"answer\":\"It proposes using ML-QEM to mimic traditional mitigation methods while achieving superior runtime efficiency, extending the practicality of QEM by reducing overheads.\"}]","Machine Learning for Practical Quantum Error Mitigation | PDF",1785673090,55,{"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-for-practical-quantum-error-mitigation","",{"@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-for-practical-quantum-error-mitigation/117015/",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","2026-08-05","2026-08-02",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 problem does ML-QEM aim to solve in practical quantum computing?","Question",{"text":76,"@type":77},"ML-QEM targets the core practical challenge of achieving accurate quantum error mitigation without excessive runtime overhead from additional mitigation circuits.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is ML-QEM evaluated in the study?",{"text":81,"@type":77},"The work benchmarks multiple machine learning models on diverse quantum circuit classes across increasingly complex device-noise profiles, using both interpolation and extrapolation and comparing against a reference digital zero-noise extrapolation method.",{"name":83,"@type":74,"acceptedAnswer":84},"What approach does the paper propose for scalable quantum error mitigation?",{"text":85,"@type":77},"It proposes using ML-QEM to mimic traditional mitigation methods while achieving superior runtime efficiency, extending the practicality of QEM by reducing overheads.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]