Time-Data Tradeoffs in Structured Signals Recovery via the Proximal-Gradient Homotopy Method

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, we characterize data-time tradeoffs of the proximal-gradient homotopy method used for solving linear inverse problems under sub-Gaussian measurements. Our results are sharp up to an absolute constant factor. We demonstrate that, in the absence of the strong convexity assumption, the proximal-gradient homotopy update can achieve a linear rate of convergence when the number of measurements is sufficiently large. Numerical simulations are provided to verify our theoretical results.

源语言英语
主期刊名2022 IEEE International Symposium on Information Theory, ISIT 2022
出版商Institute of Electrical and Electronics Engineers Inc.
1612-1616
页数5
ISBN(电子版)9781665421591
DOI
出版状态已出版 - 2022
活动2022 IEEE International Symposium on Information Theory, ISIT 2022 - Espoo, 芬兰
期限: 26 6月 20221 7月 2022

出版系列

姓名IEEE International Symposium on Information Theory - Proceedings
2022-June
ISSN(印刷版)2157-8095

会议

会议2022 IEEE International Symposium on Information Theory, ISIT 2022
国家/地区芬兰
Espoo
时期26/06/221/07/22

指纹

探究 'Time-Data Tradeoffs in Structured Signals Recovery via the Proximal-Gradient Homotopy Method' 的科研主题。它们共同构成独一无二的指纹。

引用此