No confident code implementation found for this paper. 3 possible matches can be shown below.
We propose a tensor-based criterion for benign landscape in phase retrieval and establish boundedness of gradient trajectories. This implies that gradient descent will converge to a global minimum for almost every initial point.
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
The Role of the Time-Dependent Hessian in High-Dimensional Optimization
Stable Phase Retrieval with Mirror Descent
Robust Gradient Descent for Phase Retrieval
A Smoothing Newton Method for Rank-one Matrix Recovery
Long-time dynamics and universality of nonconvex gradient descent
Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares
@article{fougereux2024global,
title = {Global convergence of gradient descent for phase retrieval},
author = {Théodore Fougereux and Cédric Josz and Xiaopeng Li},
year = {2024},
eprint = {2410.09990},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2410.09990v2}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2410.09990)