在PyTorch中改进LBFGS优化器:从无线电干涉校准到机器学习的知识转移

2018 IEEE 14th International Conference on e-Science (e-Science) Pub Date : 2018-10-01 DOI:10.1109/eScience.2018.00112

S. Yatawatta, H. Spreeuw, F. Diblen

{"title":"在PyTorch中改进LBFGS优化器:从无线电干涉校准到机器学习的知识转移","authors":"S. Yatawatta, H. Spreeuw, F. Diblen","doi":"10.1109/eScience.2018.00112","DOIUrl":null,"url":null,"abstract":"We have modified the LBFGS optimizer in PyTorch based on our knowledge in using the LBFGS algorithm in radio interferometric calibration (SAGECal). We give results to show the performance improvement of PyTorch in various machine learning applications due to our improvements.","PeriodicalId":6476,"journal":{"name":"2018 IEEE 14th International Conference on e-Science (e-Science)","volume":"91 1","pages":"386-387"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Improving LBFGS Optimizer in PyTorch: Knowledge Transfer from Radio Interferometric Calibration to Machine Learning\",\"authors\":\"S. Yatawatta, H. Spreeuw, F. Diblen\",\"doi\":\"10.1109/eScience.2018.00112\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We have modified the LBFGS optimizer in PyTorch based on our knowledge in using the LBFGS algorithm in radio interferometric calibration (SAGECal). We give results to show the performance improvement of PyTorch in various machine learning applications due to our improvements.\",\"PeriodicalId\":6476,\"journal\":{\"name\":\"2018 IEEE 14th International Conference on e-Science (e-Science)\",\"volume\":\"91 1\",\"pages\":\"386-387\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE 14th International Conference on e-Science (e-Science)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/eScience.2018.00112\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 14th International Conference on e-Science (e-Science)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/eScience.2018.00112","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

基于我们在无线电干涉校准(SAGECal)中使用LBFGS算法的知识，我们修改了PyTorch中的LBFGS优化器。我们给出的结果表明，由于我们的改进，PyTorch在各种机器学习应用程序中的性能有所提高。

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

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Improving LBFGS Optimizer in PyTorch: Knowledge Transfer from Radio Interferometric Calibration to Machine Learning

We have modified the LBFGS optimizer in PyTorch based on our knowledge in using the LBFGS algorithm in radio interferometric calibration (SAGECal). We give results to show the performance improvement of PyTorch in various machine learning applications due to our improvements.

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

2018 IEEE 14th International Conference on e-Science (e-Science)

自引率

0.00%

发文量