Phase Retrieval Under a Generative Prior

Simple item page
dc.contributor.advisorHicks, Illya
dc.contributor.committeeMemberHand, Paul
dc.creatorLeong, Oscar
dc.date.accessioned2019-05-17T16:45:56Z
dc.date.available2019-05-17T16:45:56Z
dc.date.created2018-12
dc.date.issued2019-04-11
dc.date.submittedDecember 2018
dc.date.updated2019-05-17T16:45:56Z
dc.description.abstractThe phase retrieval problem, arising from X-ray crystallography and medical imaging, asks to recover a signal given intensity-only measurements. When the number of measurements is less than the dimensionality of the signal, solving the problem requires additional assumptions, or priors, on its structure in order to guarantee recovery. Many techniques enforce a sparsity prior, meaning that the signal has very few non-zero entries. However, these methods have seen various computational bottlenecks. We sidestep this issue by enforcing a generative prior: the assumption that the signal is in the range of a generative neural network. By formulating an empirical risk minimization problem and directly optimizing over the domain of the generator, we show that the objective’s energy landscape exhibits favorable global geometry for gradient descent with information theoretically optimal sample complexity. Based on this geometric result, we introduce a gradient descent algorithm to converge to the true solution. We corroborate these results with experiments showing that exploiting generative models in phase retrieval tasks outperforms sparse phase retrieval methods.
dc.format.mimetypeapplication/pdf
dc.identifier.citationLeong, Oscar. "Phase Retrieval Under a Generative Prior." (2019) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/105890">https://hdl.handle.net/1911/105890</a>.
dc.identifier.urihttps://hdl.handle.net/1911/105890
dc.language.isoeng
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.
dc.subjectPhase Retrieval
dc.subjectGenerative Models
dc.subjectNon-convex Optimization
dc.subjectDeep Learning
dc.titlePhase Retrieval Under a Generative Prior
dc.typeThesis
dc.type.materialText
thesis.degree.departmentComputational and Applied Mathematics
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelMasters
thesis.degree.nameMaster of Arts
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LEONG-DOCUMENT-2018.pdf
Size:
22.9 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.6 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Electronic Theses and Dissertations