Back to search

University of British Columbia

Generative compressed sensing with Fourier measurements

Abstract

dc:description

In~\cite{bora2017compressed}, a mathematical framework was developed for compressed sensing guarantees in the setting where the measurement matrix is Gaussian and the signal structure is the range of a generative neural network (GNN). The problem of compressed sensing with GNNs has since been extensively analyzed when the measurement matrix and/or network weights follow a subgaussian distribution. In this thesis, we move beyond the subgaussian assumption to measurement matrices that are derived by sampling uniformly at random rows of a unitary matrix (including sub-sampled Fourier measurements as a special case). Specifically, we prove the first known restricted isometry guarantee for generative compressed sensing (GCS) with \emph{sub-sampled isometries}, and provide recovery bounds with nearly order-optimal sample complexity, addressing an open problem of~\cite[p.~10]{scarlett2022theoretical}. Recovery efficacy is characterized by the \emph{coherence}, a new parameter, which measures the interplay between the range of the network and the measurement matrix. Our approach relies on subspace counting arguments and ideas central to high-dimensional probability. Furthermore, we propose a regularization strategy for training GNNs to have favourable coherence with the measurement operator. We provide compelling numerical simulations that support this regularized training strategy: our strategy yields low coherence networks that require fewer measurements for signal recovery. This, together with our theoretical results, supports coherence as a natural quantity for characterizing GCS with sub-sampled isometries.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Mathematics
Grantor dc:publisher
University of British Columbia
Year dc:date
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Scott, Matthew
Contributors dc:contributor
  • Yilmaz, Ozgur
  • Plan, Yaniv

Rights

dc:rights
Statement dc:rights
  • Attribution-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/85784

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Scott, Matthew. Generative compressed sensing with Fourier measurements. master's thesis, University of British Columbia, 2023. http://hdl.handle.net/2429/85784