[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128092-en":3,"doc-seo-128092-105":31,"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":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},128092,687207022233,"Riley","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Sparks of Quantum Advantage and Rapid Retraining in Machine Learning","Quantum computing promises faster solutions for complex tasks, yet practical quantum advantage is constrained by limited qubit counts and high noise on current hardware. This study uses adiabatic quantum computing to optimize Kolmogorov-Arnold Networks by switching to Bézier curves as basis functions and casting training into a QUBO with a fixed solution space. The method enables optimization in a single iteration and targets extremely fast training, validated against Adam, SGD, AdaGrad, and simulated annealing. A rapid retraining mechanism allows updating with new data without reprocessing old samples, showing large speedups and suggesting broad future applications.","Sparks of Quantum Advantage and Rapid Retraining in Machine  \nLearning  \nWilliam Troy1*  \nAbstract  \nThe advent of quantum computing holds the potential to revolutionize various fields by solving complex problems more efficiently than classical computers. Despite this promise, practical quantum advantage is hindered by current hardware limitations, notably the small number of qubits and high noise levels. In this study, we leverage adiabatic quantum computers to optimize Kolmogorov-Arnold Networks, a powerful neural network architecture for representing complex functions with minimal parameters. By modifying the network to use Bézier curves as the basis functions and formulating the optimization problem into a Quadratic Unconstrained Binary Optimization problem, we create a fixed-sized solution space, independent of the number of training samples. This strategy allows for the optimization of an entire neural network in a single training iteration in which, due to order of operations, a majority of the processing is done using a collapsed version of the training dataset. This inherently creates extremely fast training speeds, which are validated experimentally, compared to classical optimizers including Adam, Stochastic Gradient Descent, Adaptive Gradient, and simulated annealing. Additionally, we introduce a novel rapid retraining capability, enabling the network tobe retrained with new data without reprocessing old samples, thus enhancing learning efficiency in dynamic environments. Experiments on retraining demonstrate a hundred times speed up using adiabatic quantum computing based optimization compared to that of the gradient descent based optimizers, with theoretical models allowing this speed up to be much larger! Our findings suggest that with further advancements in quantum hardware and algorithm optimization, quantum-optimized machine learning models could have broad applications across various domains, with initial focus on rapid retraining.  \n1. Introduction  \nThe advent of quantum computing (QC) promises to revolutionize various fields by solving complex problems more efficiently than classical computers. This is possible as quantum computers leverage the principles of superposition and entanglement to perform computations that would be infeasible for classical computers, potentially offering exponential speedups for certain types of problems 1–3. For instance, Shor's algorithm for factoring large numbers can theoretically break widely used cryptographic systems much faster than the best classical algorithms4. Despite this promise, the practical realization of quantum advantage is hindered by current limitations in quantum hardware, notably the relatively small number of qubits and high noise levels on modern quantum processors. These limitations make it challenging to solve large-scale problems and require highly optimized algorithms to make the most of the existing  \n1 Independent Researcher  \n* Corresponding Author: [troywilliame@gmail.com](troywilliame@gmail.com)  \nquantum resources5. To date, quantum advantage has only been demonstrated a couple of times, notably by Google’s Sycamore processor and in Gaussian boson sampling experiments6,7.  \nWhile these achievements mark significant milestones, quantum advantage in other domains remains difficult to achieve. A particularly promising area of application for QC is quantum machine learning (QML), which integrates quantum computing with machine learning techniques to leverage quantum speedups for training and inference tasks8–10. Platforms like TensorFlow and Qiskit have already started integrating quantum models, providing tools for researchers to explore QML applications 11, 12. Despite these advancements, Google recently highlighted a significant gap in the field at Google I/O 2024, stating that no one has yet demonstrated a clear quantum advantage for machine learning on classical data 11 This gap underscores the need for innovative approaches that can bridge ","cbCaibJTyhWaXnN5","https://ap.wps.com/l/cbCaibJTyhWaXnN5","pdf",709239,2,1,17,"English","en",105,"# Abstract\n# Introduction\n## Quantum advantage and hardware limitations\n## Quantum machine learning gap on classical data\n## Adiabatic optimization of Bézier KANs via QUBO","[{\"question\":\"Why is practical quantum advantage difficult to achieve today?\",\"answer\":\"Current quantum hardware limits the process with small qubit counts and high noise, which makes large-scale optimization and training challenging without highly optimized methods.\"},{\"question\":\"How does the study optimize Kolmogorov-Arnold Networks using adiabatic quantum computing?\",\"answer\":\"It reformulates the KAN optimization into a QUBO by using Bézier curves as basis functions, then uses order-of-operations simplifications and an adiabatic quantum annealer to find optimal weights.\"},{\"question\":\"What is the rapid retraining capability and how does it improve learning efficiency?\",\"answer\":\"The network can be retrained on new data without reprocessing old samples. This reduces retraining cost in dynamic environments and enables large speedups versus gradient-based optimizers, with reported hundred-fold improvements.\"}]","Sparks of Quantum Advantage and Rapid Retraining in Machine Learning | PDF",1785944755,43,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"sparks-of-quantum-advantage-and-rapid-retraining-in-machine-learning","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/sparks-of-quantum-advantage-and-rapid-retraining-in-machine-learning/128092/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",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},"Why is practical quantum advantage difficult to achieve today?","Question",{"text":76,"@type":77},"Current quantum hardware limits the process with small qubit counts and high noise, which makes large-scale optimization and training challenging without highly optimized methods.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the study optimize Kolmogorov-Arnold Networks using adiabatic quantum computing?",{"text":81,"@type":77},"It reformulates the KAN optimization into a QUBO by using Bézier curves as basis functions, then uses order-of-operations simplifications and an adiabatic quantum annealer to find optimal weights.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the rapid retraining capability and how does it improve learning efficiency?",{"text":85,"@type":77},"The network can be retrained on new data without reprocessing old samples. This reduces retraining cost in dynamic environments and enables large speedups versus gradient-based optimizers, with reported hundred-fold improvements.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]