基于图像分割的AdaMax算法的遗憾边界

IF 2.1 3区数学 Q1 MATHEMATICS, APPLIED

Mathematical Methods in the Applied Sciences Pub Date : 2025-03-09 DOI:10.1002/mma.10879

Wachirapong Jirakitpuwapat

{"title":"基于图像分割的AdaMax算法的遗憾边界","authors":"Wachirapong Jirakitpuwapat","doi":"10.1002/mma.10879","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>The AdaMax algorithm provides enhanced convergence properties for stochastic optimization problems. In this paper, we present a regret bound for the AdaMax algorithm, offering a tighter and more refined analysis compared to existing bounds. This theoretical advancement provides deeper insights into the optimization landscape of machine learning algorithms. Specifically, the You Only Look Once (YOLO) framework has become well-known as an extremely effective object segmentation tool, mostly because of its extraordinary accuracy in real-time processing, which makes it a preferred option for many computer vision applications. Finally, we used this algorithm for image segmentation.</p>\n </div>","PeriodicalId":49865,"journal":{"name":"Mathematical Methods in the Applied Sciences","volume":"48 9","pages":"10208-10214"},"PeriodicalIF":2.1000,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Regret Bound for the AdaMax Algorithm With Image Segmentation Application\",\"authors\":\"Wachirapong Jirakitpuwapat\",\"doi\":\"10.1002/mma.10879\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>The AdaMax algorithm provides enhanced convergence properties for stochastic optimization problems. In this paper, we present a regret bound for the AdaMax algorithm, offering a tighter and more refined analysis compared to existing bounds. This theoretical advancement provides deeper insights into the optimization landscape of machine learning algorithms. Specifically, the You Only Look Once (YOLO) framework has become well-known as an extremely effective object segmentation tool, mostly because of its extraordinary accuracy in real-time processing, which makes it a preferred option for many computer vision applications. Finally, we used this algorithm for image segmentation.</p>\\n </div>\",\"PeriodicalId\":49865,\"journal\":{\"name\":\"Mathematical Methods in the Applied Sciences\",\"volume\":\"48 9\",\"pages\":\"10208-10214\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2025-03-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mathematical Methods in the Applied Sciences\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/mma.10879\",\"RegionNum\":3,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICS, APPLIED\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mathematical Methods in the Applied Sciences","FirstCategoryId":"100","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mma.10879","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}

引用次数: 0

摘要

AdaMax算法为随机优化问题提供了更强的收敛性。在本文中，我们提出了一个遗憾界的AdaMax算法，提供了一个更严格和更精细的分析相比，现有的边界。这一理论进步为机器学习算法的优化领域提供了更深入的见解。具体来说，You Only Look Once （YOLO）框架已经成为一种非常有效的对象分割工具，主要是因为它在实时处理中具有非凡的准确性，这使得它成为许多计算机视觉应用程序的首选。最后，将该算法应用于图像分割。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Regret Bound for the AdaMax Algorithm With Image Segmentation Application

The AdaMax algorithm provides enhanced convergence properties for stochastic optimization problems. In this paper, we present a regret bound for the AdaMax algorithm, offering a tighter and more refined analysis compared to existing bounds. This theoretical advancement provides deeper insights into the optimization landscape of machine learning algorithms. Specifically, the You Only Look Once (YOLO) framework has become well-known as an extremely effective object segmentation tool, mostly because of its extraordinary accuracy in real-time processing, which makes it a preferred option for many computer vision applications. Finally, we used this algorithm for image segmentation.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Mathematical Methods in the Applied Sciences 数学-应用数学

CiteScore

4.90

自引率

6.90%

发文量

798

审稿时长

6 months

期刊介绍： Mathematical Methods in the Applied Sciences publishes papers dealing with new mathematical methods for the consideration of linear and non-linear, direct and inverse problems for physical relevant processes over time- and space- varying media under certain initial, boundary, transition conditions etc. Papers dealing with biomathematical content, population dynamics and network problems are most welcome. Mathematical Methods in the Applied Sciences is an interdisciplinary journal: therefore, all manuscripts must be written to be accessible to a broad scientific but mathematically advanced audience. All papers must contain carefully written introduction and conclusion sections, which should include a clear exposition of the underlying scientific problem, a summary of the mathematical results and the tools used in deriving the results. Furthermore, the scientific importance of the manuscript and its conclusions should be made clear. Papers dealing with numerical processes or which contain only the application of well established methods will not be accepted. Because of the broad scope of the journal, authors should minimize the use of technical jargon from their subfield in order to increase the accessibility of their paper and appeal to a wider readership. If technical terms are necessary, authors should define them clearly so that the main ideas are understandable also to readers not working in the same subfield.