Robust gradient descent for phase retrieval

Recent progress in robust statistical learning has mainly tackled convex problems, like mean estimation or linear regression, with non-convex challenges receiving less attention. Phase retrieval exemplifies such a nonconvex problem, requiring the recovery of a signal from only the magnitudes of its...

Full description

Bibliographic Details
Main Authors: Buna-Marginean, A, Rebeschini, P
Format: Conference item
Language:English
Published: PMLR 2025