REVIEW 3 cited by
Exact asymptotics for phase retrieval and compressed sensing with random generative priors
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We consider the problem of compressed sensing and of (real-valued) phase retrieval with random measurement matrix. We derive sharp asymptotics for the information-theoretically optimal performance and for the best known polynomial algorithm for an ensemble of generative priors consisting of fully connected deep neural networks with random weight matrices and arbitrary activations. We compare the performance to sparse separable priors and conclude that generative priors might be advantageous in terms of algorithmic performance. In particular, while sparsity does not allow to perform compressive phase retrieval efficiently close to its information-theoretic limit, it is found that under the random generative prior compressed phase retrieval becomes tractable.
Forward citations
Cited by 3 Pith papers
-
Optimal spectral initializers impact on phase retrieval phase transitions -- an RDT view
Optimal spectral initializers at the theoretical phase retrieval threshold sit in flat landscape regions, so roughly 15% oversampling is needed for reliable descending algorithms.
-
Phase transition of \emph{descending} phase retrieval algorithms
The paper derives RDT-based lower bounds and predicts a phase transition at oversampling ratio α≈1.4 where descending phase retrieval algorithms transition from failing to succeeding, but the key isomorphism with conv...
-
Phase retrieval with rank $d$ measurements -- \emph{descending} algorithms phase transitions
For rank d phase retrieval with Gaussian measurements, descending gradient algorithms are predicted to succeed above a sample complexity ratio near 2.79 for d=2, with lifted bounds lowering this estimate and simulatio...
Discussion (0). Continue with ORCID to comment.