Home
Resource
Optimization problems with low-dimensional tensor structure
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(748.86 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Kwon, Soo Min. Optimization problems with low-dimensional tensor structure. Retrieved from https://doi.org/doi:10.7282/t3-snj7-3a69

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleOptimization problems with low-dimensional tensor structure
NameKwon, Soo Min (author); Sarwate, Anand (chair); Zhang, Yuqian (member); Jalali, Shirin (member); Rutgers University; School of Graduate Studies
Date Created2022
Other Date2022-05 (degree)
SubjectElectrical engineering, Statistics, Non-convex optimization, Tensor decomposition
Extent59 pages : illustrations
DescriptionIn this thesis, we consider optimization problems that involve statistically estimating signals from tensor data. We observe that modelling the signals as tensors using tensor factorizations increases the accuracy of more closely estimating the true signal. We empirically show that this is a result of two reasons: (i) it reduces the number of parameters that need to be estimated, hinting at a decrease in sample complexity, and (ii) it allows us to take advantage of the low-rank property that many high-dimensional tensor data samples possess. We also show that while there exists a tradeoff between the accuracy of the reconstructed signal and the ranks according to the tensor decomposition, there often exists a rank that improves performance in sample-starved settings. We discuss these tradeoffs and develop algorithms for two of these applications, classification and phase retrieval, and demonstrate the effectiveness of our algorithms under several different settings and performance metrics.
NoteM.S.
NoteIncludes bibliographical references
Genretheses
Persistent URLhttps://doi.org/doi:10.7282/t3-snj7-3a69
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024