摘要 : This paper studies early-stopped mirror descent applied to noisy sparse phase retrieval, which is the problem of recovering a $k$ -sparse signal $\textbf{x}^\star \in{\mathbb{R}}^n$ from a set of quadratic Gaussian measurements... 展开
作者 | Fan Wu Patrick Rebeschini |
---|---|
作者单位 | |
期刊名称 | 《Information and Inference: A Journal of the IMA》 |
页码/总页数 | 633-713 / 81 |
语种/中图分类号 | 英语 / TP3 |
关键词 | mirror descent early stopping sparsity minimax rate implicit regularization non-convex empirical risk phase retrieval |
DOI | 10.1093/imaiai/iaac024 |
馆藏号 | IELEP0532 |