Data-driven Smooth-to-hard Spectral Regularization for General Linear Inverse Problems

2026-10-16来源 arXiv eess.IVEnglish
arXiv:2610.21664v1 Announce Type: cross Abstract: The logistic smooth-to-hard shrinker is the proximal map of an explicit saturating spectral penalty for general linear inverse problems. Its exact weak convexity yields a unique scaled update and proximal-gradient stationarity guarantees, while independent validation provides finite-grid parameter-selection control. We use MRI as an illustrative example.

原文：https://www.a8q9.cn/en/article/data-driven-smooth-to-hard-spectral-regularization-for-general-linear-inverse-pr-492324.html

相关文章