Abstract
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.
Global convergence of gradient descent for phase retrieval
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval (2026)66% match
- Robust Gradient Descent for Phase Retrieval (2024)65% match
- Stable Phase Retrieval with Mirror Descent (2024)63% match
- Phase transition of \emphdescending phase retrieval algorithms (2025)62% match
- Smoothed Robust Phase Retrieval (2024)61% match
- Low Complexity Regularized Phase Retrieval (2024)60% match
- Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval (2026)60% match
- Self-supervised learning for phase retrieval (2025)58% match