|国家预印本平台
首页|A Smoothing Newton Method for Rank-one Matrix Recovery

A Smoothing Newton Method for Rank-one Matrix Recovery

A Smoothing Newton Method for Rank-one Matrix Recovery

来源:Arxiv_logoArxiv
英文摘要

We consider the phase retrieval problem, which involves recovering a rank-one positive semidefinite matrix from rank-one measurements. A recently proposed algorithm based on Bures-Wasserstein gradient descent (BWGD) exhibits superlinear convergence, but it is unstable, and existing theory can only prove local linear convergence for higher rank matrix recovery. We resolve this gap by revealing that BWGD implements Newton's method with a nonsmooth and nonconvex objective. We develop a smoothing framework that regularizes the objective, enabling a stable method with rigorous superlinear convergence guarantees. Experiments on synthetic data demonstrate this superior stability while maintaining fast convergence.

Tyler Maunu、Gabriel Abreu

数学

Tyler Maunu,Gabriel Abreu.A Smoothing Newton Method for Rank-one Matrix Recovery[EB/OL].(2025-07-30)[2025-08-07].https://arxiv.org/abs/2507.23017.点此复制

评论