Cornell University
NEW PERSPECTIVES ON CONTINUOUS OPTIMIZATION: THEORY AND METHODOLOGY
Abstract
dc:description.abstractLarge-scale continuous optimization arises in many practical problems such as machine learning, signal processing, and imaging. It is usually challenging to analyze the theoretical properties of optimization algorithms and design scalable algorithms that work well in practice. This dissertation provides new perspectives on continuous optimization in both theory and methodology. From the theoretical side, we present a framework for reasoning about equivalence between a broad class of iterative convex continuous optimization algorithms. The notion of algorithm equivalence can make it easier to understand the connections between optimization algorithms, relate many analytical properties of interest such as convergence or robustness, and further give insights to design new algorithms. From the methodological side, we first present NysADMM, a scalable algorithm for faster composite convex optimization by exploiting the low-rank structure. NysADMM accelerates the inexact linearized Alternating Direction Method of Multipliers (ADMM) by constructing a preconditioner for the ADMM subproblem from a randomized low-rank Nystr{\"o}m approximation. Second, we present GeNI-ADMM, a framework generalized from NysADMM, which encompasses any ADMM algorithm that solves a first- or (generalized) second-order approximation to the ADMM subproblem and allows inexact subproblem solves. It facilitates the theoretical analysis of various approximate ADMM schemes for large-scale composite convex optimization.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Systems Engineering
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Systems Engineering
- Grantor
- Cornell University
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zhao, Shipu
- Chair dc:contributor.chair
-
- Udell, Madeleine
- Committee members dc:contributor.committeemember
-
- Gao, Huaizhu
- Bitar, Eilyan
Subjects
dc:subject × 4Rights
dc:rights- Statement dc:rights
-
- Attribution 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 16176459
- Dc Identifier Other
-
ProQuest Submission ID: 13501
ProQuest Publication ID: 30312922