[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122038-en":3,"doc-seo-122038-105":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},122038,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","QuaLITi - Quantum Machine Learning Hardware Selection for Inferencing with Top-Tier Performance","Quantum Machine Learning (QML) uses quantum computing principles to improve machine learning methods, but NISQ devices introduce noise that corrupts qubit states and degrades training and inferencing accuracy. Real hardware also involves long access queues, where a fixed-shot execution may wait hours, harming iterative QML workflows. Many works rely on simulators or reduced datasets; this study analyzes quantum classifier inferencing and training under noise and varied hardware and coupling maps, leveraging hardware queue wait times. Results show multi-hardware training can reduce training wait time up to 45X with only 3–4% performance impact.","QuaLITi: Quantum Machine Learning Hardware Selection for Inferencing with Top-Tier Performance  \nKoustubh Phalak  \nCSE Department Pennsylvania State University State College, PA[krp5448@psu.edu](krp5448@psu.edu)  \nSwaroop Ghosh  \nSchool of EECS Pennsylvania State University State College, PA[szg212@psu.edu](szg212@psu.edu)  \narXiv :2405 . 11194v1 [ quant-ph] 18 May 2024  \nAbstract—Quantum Machine Learning (QML) is an accelerating field of study that leverages the principles of quantum computing to enhance and innovate within machine learning methodologies. However, Noisy Intermediate-Scale Quantum (NISQ) computers suffer from noise that corrupts the quantum states of the qubits and affects the training and inferencing accuracy. Furthermore, quantum computers have long access queues. A single execution with a pre-defined number of shots can take hours just to reach the top of the wait queue, which is especially disadvantageous to Quantum Machine Learning (QML) algorithms that are iterative in nature. Many vendors provide access to a suite of quantum hardware with varied qubit technologies, number of qubits, coupling architectures, and noise characteristics. However, present QML algorithms do not use them for the training procedure and often rely on local noiseless/noisy simulators due to cost and training timing overhead on real hardware. Additionally, inferencing is generally performed on reduced datasets with fewer datapoints. Taking these constraints into account, we perform a study to maximize the inferencing performance of QML workloads based on the choice of hardware selection. Specifically, we perform a detailed analysis of quantum classifiers (both training and inference through the lens of hardware queue wait times) on Iris and reduced Digits datasets under noise and varied conditions such as different hardware and coupling maps. We show that using multiple readily available hardware for training rather than relying on a single hardware, especially if it has a long queue depth of pending jobs, can lead to a performance impact of only 3-4% while providing up to 45X reduction in training wait time.  \nIndex Terms—Quantum Hardware, Quantum Machine Learning, Inferencing  \nI. INTRODUCTION  \nIn recent years, the field of quantum computing has witnessed significant growth, propelled by its potential to solve complex problems far beyond the reach of classical computing paradigms [1] . This emerging technology, characterized by its principles of superposition, entanglement, and quantum interference, offers unprecedented computational advantages, promising revolutionary breakthroughs [2], [3] in various disciplines, including cryptography [4], finance [5],[6], chemistry and material science [7], and healthcare [8] . One of the most promising applications of quantum computing lies in the domain of machine learning, where the computational advantages of quantum algorithms can be leveraged to enhance the efficiency and capability of traditional machine learning  \n [9,10,11,12,17,30,29,28]  \nOR  \n [79,80,81,82,83,84,85,86]  \n(61%)  \n(61%)  \n OR  \n[97,98,99,100,110,118,119,120]  \n (66%)  \nFig. 1. Training reduced Digits dataset (classes 8,9) on randomly allocated configurations gives poor inferencing results. The training is done on 127 qubit hardware where we observe a maximum inferencing performance up to 66%, suggesting that there is room for improvement with regards to the choice of qubit configuration and even hardware.  \nalgorithms [9] . The synthesis of quantum computing and machine learning has given rise to a new interdisciplinary field known as Quantum Machine Learning (QML), which seeks to harness quantum computational advantages to improve machine learning tasks. Examples of quantum machine learning algorithms, such as Quantum Neural Networks (QNN)  \n[10], Variational Quantum Eigensolver (VQE) [11], Variational Quantum Classifier (VQC) [12], and Quantum Support Vector Machine (QSVM) [13], illustrate the potential of quantu","cbCairM7ZxFxG10h","https://ap.wps.com/l/cbCairM7ZxFxG10h","pdf",1116714,1,9,"English","en",105,"# Introduction\n## QML and NISQ constraints\n## Hardware noise and coupling maps\n# Methodology\n## Multi-hardware training and configurational analysis\n## Selecting top configurations\n# Results\n## Inferencing performance on Iris and reduced Digits","[{\"question\":\"Why do NISQ noise and hardware queue wait times limit quantum machine learning performance?\",\"answer\":\"Noise such as gate errors, decoherence, and crosstalk corrupts qubit states and reduces training/inferencing accuracy. Long queue access times mean even a single fixed-shot execution can wait hours, which is especially harmful for iterative QML training loops.\"},{\"question\":\"What hardware-related factors are analyzed in the study?\",\"answer\":\"The study evaluates quantum classifiers under different hardware choices and coupling maps, considering properties like coherence times, error rates, and circuit depth to assign scores to configurations before training.\"},{\"question\":\"How does multi-hardware training compare with training on a single hardware device?\",\"answer\":\"Using multiple readily available hardware devices for training, rather than relying on one device with a long pending-job queue depth, can reduce training wait time by up to 45X while causing only about a 3–4% performance impact.\"}]","QuaLITi - Quantum Machine Learning Hardware Selection for Inferencing with Top-Tier Performance | PDF",1785808479,23,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"qualiti-quantum-machine-learning-hardware-selection-for-inferencing-with-top-tier-performance","",{"@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/qualiti-quantum-machine-learning-hardware-selection-for-inferencing-with-top-tier-performance/122038/",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","2026-08-04",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 do NISQ noise and hardware queue wait times limit quantum machine learning performance?","Question",{"text":75,"@type":76},"Noise such as gate errors, decoherence, and crosstalk corrupts qubit states and reduces training/inferencing accuracy. Long queue access times mean even a single fixed-shot execution can wait hours, which is especially harmful for iterative QML training loops.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What hardware-related factors are analyzed in the study?",{"text":80,"@type":76},"The study evaluates quantum classifiers under different hardware choices and coupling maps, considering properties like coherence times, error rates, and circuit depth to assign scores to configurations before training.",{"name":82,"@type":73,"acceptedAnswer":83},"How does multi-hardware training compare with training on a single hardware device?",{"text":84,"@type":76},"Using multiple readily available hardware devices for training, rather than relying on one device with a long pending-job queue depth, can reduce training wait time by up to 45X while causing only about a 3–4% performance impact.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]