Phase transition of \emph{descending} phase retrieval algorithms
We study theoretical limits of \emph{descending} phase retrieval algorithms. Utilizing \emph{Random duality theory} (RDT) we develop a generic program that allows statistical characterization of various algorithmic performance metrics. Through these we identify the concepts of \emph{parametric manifold} and its \emph{funneling points} as key mathematical objects that govern the underlying algorithms' behavior. An isomorphism between single funneling point manifolds and global convergence of descending algorithms is established. The structure and shape of the parametric manifold as well as its dependence on the sample complexity are studied through both plain and lifted RDT. Emergence of a phase transition is observed. Namely, as sample complexity increases, parametric manifold transitions from a multi to a single funneling point structure. This in return corresponds to a transition from the scenarios where descending algorithms generically fail to the scenarios where they succeed in solving phase retrieval. We also develop and implement a practical algorithmic variant that in a hybrid alternating fashion combines a barrier and a plain gradient descent. Even though the theoretical results are obtained for infinite dimensional scenarios (and consequently non-jittery parametric manifolds), we observe a strong agrement between theoretical and simulated phase transitions predictions for fairly small dimensions on the order of a few hundreds.
Jun-24-2025
- Country:
- Africa > Sudan (0.04)
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Maryland (0.04)
- Washington > King County
- Seattle (0.04)
- Texas
- Dallas County > Dallas (0.04)
- Travis County > Austin (0.04)
- New Jersey > Mercer County
- Princeton (0.04)
- Massachusetts > Plymouth County
- Norwell (0.04)
- Colorado > Denver County
- Denver (0.04)
- California > Monterey County
- Pacific Grove (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Switzerland > Vaud
- Lausanne (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Italy > Lazio
- Rome (0.04)
- Germany > North Rhine-Westphalia
- Cologne Region > Aachen (0.04)
- Switzerland > Vaud
- Asia > Middle East
- Jordan (0.04)
- Genre:
- Research Report (0.64)
- Technology: