Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 123 for “"nonconvex optimization"”.
-
Tensor methods for nonconvex optimization
… Newton-type methods have dominated the field of optimization. In recent years, <em>high-order tensor</em> <em>methods with regularization</em> for nonconvex optimization have garnered significant research interest. These methods offer superior local convergence rates and improved worst-case …
-
Convex and nonconvex optimization geometries
… and signal processing problems are fundamentally nonconvex. One way to solve them is to transform them into convex optimization problems (a.k.a. convex relaxation), which constitutes a major part of my research. Although the convex relaxation approach is elegant in some ways that it can give …
-
Nonconvex Optimization Methods Under Inexact Information
… convergence analysis of algorithms for solving nonconvex optimization problems under inexact first-order information. We introduce Inexact Reduced Gradient (IRG) methods for general smooth functions and Inexact Gradient Descent (IGD) methods for $\mathcal{C}^{1,1}_L$ functions with relative and …
-
ON RICCATI EQUATIONS IN NONCONVEX OPTIMIZATION
Convex optimization serves as a foundational pillar for modern engineering and data science, providing highly efficient algorithms that reliably converge to a global optimal solution across diverse modeling applications. However many problems in engineering and data-science fall outside of the …
-
Nonconvex Optimization Methods: Iteration Complexity And Applications
Nowadays, optimization algorithms have become an essential tool for a large variety of applications in many fields. Despite the hardness of nonconvexity, a large number of these applications are dealing with nonconvex optimization problems. In this thesis, we shall focus on several different …
-
Distributed nonconvex optimization algorithms with compressed communication
In recent years, distributed optimization has received considerable attention and has been applied in power systems, sensor networks, and machine learning. In distributed optimization, each network agent performs local computations based on its own information exchanged with neighboring agents …
-
Analysis of Convex Relaxations for Nonconvex Optimization
Nonconvex optimizations are ubiquitous in many application fields. One important aspect of dealing with a nonconvex optimization problem is to study its convex relaxation, which is often part of some approximation algorithms that can find quality solutions to the original nonconvex problem. In this …
-
NONSMOOTH NONCONVEX OPTIMIZATION AND ROBUST CONVEX MODELS
… thesis develops complementary perspectives on optimization, combining theoretical advances in nonsmooth nonconvex algorithms and applied models for decision-making under uncertainty, emphasizing both rigor and applicability. In nonsmooth nonconvex optimization, stochastic gradient methods are …
-
Bayesian coresets: Revisiting the nonconvex optimization perspective
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
Quantum Algorithms for Nonconvex Optimization: Theory and Implementation
Continuous optimization problems arise in virtually all disciplines of quantitative research. While convex optimization has been well-studied in recent decades, large-scale nonconvex optimization problems remain intractable in both theory and practice. Quantum computers are expected to outperform …
-
Finite element model updating through smooth nonconvex optimization
… FE model updating is formulated as optimization problem aiming to minimize the difference between simulated and experimentally-measured modal properties. This research focuses on three frequency-domain model updating formulations, i.e. MAC value, eigenvector difference and modal …
-
Essays on Statistical Inference, Nonconvex Optimization and Machine Learning
Over the past decades, numerous optimization and machine learning (ML) algorithms have been proposed, many of which have demonstrated success in real-world applications and significantly impacted people's lives. Researchers have devoted considerable effort to understanding the theoretical …
-
Regularities in variational analysis and their applications in nonconvex optimization
… splitting method—a convex optimization algorithm—and its variations to nonconvex setting, both with and without a traditional assumption on Lipschitz smoothness. Our analysis hinges on analyzing merit functions associated with nonconvex extensions of the …
-
Convex and Nonconvex Optimization Techniques for Multifacility Location and Clustering
… rules for generalized differentiation and optimization methods for solving nonsmooth nonconvex problems with applications to multifacility location and clustering. A variational geometric approach is used for developing calculus rules for subgradients and Fenchel conjugates of convex …
-
Generalized Coderivative-Based Newtonian Methods In Nonsmooth Nonconvex Optimization And Applications
… and develops new Newton-type methods to solve nonconvex and nonsmooth optimization problems with justifying their fast local and global convergence by means of advanced tools of variational analysis and generalized differentiation. The objective functions belong to a broad class of prox-regular …
-
Nonconvex Optimization Methods with Applications to Portfolio Selection and Hybrid Systems
… formulating selection problems using continuous optimization, and solving them by specialized algorithms. Problems involving selection, i.e., selecting ``best" candidate(s) out of a given set, occur frequently in various applications, and can be formulated as nonconvex optimization problems. We …
-
Compute Faster and Learn Better: Model-based Nonconvex Optimization for Machine Learning
Nonconvex optimization naturally arises in many machine learning problems. Machine learning researchers exploit various nonconvex formulations to gain modeling flexibility, estimation robustness, adaptivity, and computational scalability. Although classical computational complexity theory has shown …
-
AUGMENTED LAGRANGIAN BASED ALGORITHMS FOR NONCONVEX OPTIMIZATION WITH APPLICATIONS IN SUBSPACE CLUSTERING
… analysis, and implementation of algorithms for nonconvex optimization that utilize the augmented Lagrangian function. In the first part of the thesis, we address general nonconvex optimization problems that have smooth objective and constraint functions. Observing a potential drawback of a …
-
Convex and structured nonconvex optimization for modern machine learning: Complexity and algorithms
In this thesis, we investigate various optimization problems motivated by applications in modern-day machine learning. In the first part, we look at the computational complexity of training ReLU neural networks. We consider the following problem: given a fully-connected two hidden layer ReLU neural …
-
Fast First-Order Methods for Large-Scale Nonconvex Optimization and Semidefinite Programming
… unconstrained convex/strongly convex composite optimization problems, linearly-constrained nonconvex composite optimization problems, and semidefinite programs. We show through extensive computational experiments that the algorithms developed in this thesis are anywhere from 5 to 100 times …
Page 1 of 7