Under a deep image prior, the mean squared error of maximum likelihood reconstruction in undersampled multilook coherent imaging is bounded by C1 times n k log n/(m^2 L) plus sqrt(k log n)/m, and a bagged projected gradient descent algorithm is provided.
Using black-box compression algorithms for phase retrieval,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multilook Coherent Imaging: Theoretical Guarantees and Algorithms
Under a deep image prior, the mean squared error of maximum likelihood reconstruction in undersampled multilook coherent imaging is bounded by C1 times n k log n/(m^2 L) plus sqrt(k log n)/m, and a bagged projected gradient descent algorithm is provided.