Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.18282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911018962124800 |
|---|---|
| author | Stojnic, Mihailo |
| author_facet | Stojnic, Mihailo |
| contents | Companion paper [118] developed a powerful \emph{Random duality theory} (RDT) based analytical program to statistically characterize performance of \emph{descending} phase retrieval algorithms (dPR) (these include all variants of gradient descents and among them widely popular Wirtinger flows). We here generalize the program and show how it can be utilized to handle rank $d$ positive definite phase retrieval (PR) measurements (with special cases $d=1$ and $d=2$ serving as emulations of the real and complex phase retrievals, respectively). In particular, we observe that the minimal sample complexity ratio (number of measurements scaled by the dimension of the unknown signal) which ensures dPR's success exhibits a phase transition (PT) phenomenon. For both plain and lifted RDT we determine phase transitions locations. To complement theoretical results we implement a log barrier gradient descent variant and observe that, even in small dimensional scenarios (with problem sizes on the order of 100), the simulated phase transitions are in an excellent agreement with the theoretical predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Phase retrieval with rank $d$ measurements -- \emph{descending} algorithms phase transitions Stojnic, Mihailo Machine Learning Information Theory Companion paper [118] developed a powerful \emph{Random duality theory} (RDT) based analytical program to statistically characterize performance of \emph{descending} phase retrieval algorithms (dPR) (these include all variants of gradient descents and among them widely popular Wirtinger flows). We here generalize the program and show how it can be utilized to handle rank $d$ positive definite phase retrieval (PR) measurements (with special cases $d=1$ and $d=2$ serving as emulations of the real and complex phase retrievals, respectively). In particular, we observe that the minimal sample complexity ratio (number of measurements scaled by the dimension of the unknown signal) which ensures dPR's success exhibits a phase transition (PT) phenomenon. For both plain and lifted RDT we determine phase transitions locations. To complement theoretical results we implement a log barrier gradient descent variant and observe that, even in small dimensional scenarios (with problem sizes on the order of 100), the simulated phase transitions are in an excellent agreement with the theoretical predictions. |
| title | Phase retrieval with rank $d$ measurements -- \emph{descending} algorithms phase transitions |
| topic | Machine Learning Information Theory |
| url | https://arxiv.org/abs/2506.18282 |