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. |
| 页 | 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 2022 → 1 7月 2022 |
出版系列
| 姓名 | IEEE International Symposium on Information Theory - Proceedings |
|---|---|
| 卷 | 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 |
| 市 | Espoo |
| 时期 | 26/06/22 → 1/07/22 |
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
Lv, X., Cui, W., & Liu, Y. (2022). Time-Data Tradeoffs in Structured Signals Recovery via the Proximal-Gradient Homotopy Method. 在 2022 IEEE International Symposium on Information Theory, ISIT 2022 (页码 1612-1616). (IEEE International Symposium on Information Theory - Proceedings; 卷 2022-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT50566.2022.9834548