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 21 for “"First-order algorithms"”.

  1. First-Order Algorithms for Nonlinear Structured Optimization

    … In this work, we present two methods which use first-order information to solve two typical classes of nonlinear structured optimization problems. For a class of unconstrained nonconvex composite optimization problems where the objective is the sum of a smooth but possibly nonconvex function and …

    lsu-thes Repository record for First-Order Algorithms for Nonlinear Structured Optimization (opens in a new tab)

  2. First-Order Algorithms for Convex Smooth Optimization Problems With Homogeneous Linear Constraints

    … purpose of this dissertation is to explore the first-order methods that can be used to solve an approximate solution for convex smooth problems with homogeneous linear constraints. It consists of three interconnected research projects. In the first project, we study the problem of computing the …

    clemson Repository record for First-Order Algorithms for Convex Smooth Optimization Problems With Homogeneous Linear Constraints (opens in a new tab)

  3. First-Order Algorithms for Unconstrained/Constrained Dynamic Games and Identification of Linear Dynamic Systems with Multiplicative Noise

    The thesis consists of two parts or works. The first part focuses on numerical methods for computing the Nash equilibria of unconstrained and constrained dynamics games, and the second one studies linear system identification with multiplicative noise. We approach both topics from the angles of …

    umn Repository record for First-Order Algorithms for Unconstrained/Constrained Dynamic Games and Identification of Linear Dynamic Systems with Multiplicative Noise (opens in a new tab)

  4. Fast Unit-modulus Least Squares with Applications in Beamforming and Phase Retrieval

    … ULS/UQP. In this paper, we propose several first-order algorithms that meet or exceed SDR performance in terms of minimizing the cost function, and compare favorably to SDR in terms of runtime complexity. We establish convergence of the proposed first-order algorithms to a KKT point, and we …

    umn Repository record for Fast Unit-modulus Least Squares with Applications in Beamforming and Phase Retrieval (opens in a new tab)

  5. Control Theory Oriented Analysis and Design of Optimisation Algorithms

    … to the design and analysis of optimization algorithms, with a focus on first-order gradient-based methods using constant step sizes. Classical techniques from control theory, including the circle criterion, gain margin optimization, and the internal model principle, are employed to establish …

    anu Repository record for Control Theory Oriented Analysis and Design of Optimisation Algorithms (opens in a new tab)

  6. Local Graph Clustering Using l1-regularized PageRank Algorithms

    … solution. In addition, we compare 6 optimization algorithms for solving the l1-regularized PageRank problem in large graphs. We demonstrate that the proposed coordinate descent outperforms the original proximal gradient descent, and the accelerated first order algorithms have the best performance …

    waterloo Repository record for Local Graph Clustering Using l1-regularized PageRank Algorithms (opens in a new tab)

  7. PERFORMANCE ANALYSIS OF OPTIMIZATION ALGORITHMS USING SEMIDEFINITE PROGRAMMING

    … for systematizing the performance analysis of first-order black-box optimization algorithms for unconstrained convex minimization problems. Through our method, we derive worst-case upper bounds on the convergence rates of the algorithms, over a fixed class of functions. Our approach is based on …

    nus Repository record for PERFORMANCE ANALYSIS OF OPTIMIZATION ALGORITHMS USING SEMIDEFINITE PROGRAMMING (opens in a new tab) Download file for PERFORMANCE ANALYSIS OF OPTIMIZATION ALGORITHMS USING SEMIDEFINITE PROGRAMMING (opens in a new tab)

  8. AUGMENTED LAGRANGIAN BASED ALGORITHMS FOR CONVEX OPTIMIZATION PROBLEMS WITH NON-SEPARABLE L1-REGULARIZATION

    … and comparison, we also summarize/design three first-order methods to solve the problem under consideration. Numerical experiments show that the SSNAL algorithm performs favourably in comparison to several state-of-the-art first-order algorithms. In addition, we propose an L1+L2 norm fidelity …

    nus Repository record for AUGMENTED LAGRANGIAN BASED ALGORITHMS FOR CONVEX OPTIMIZATION PROBLEMS WITH NON-SEPARABLE L1-REGULARIZATION (opens in a new tab) Download file for AUGMENTED LAGRANGIAN BASED ALGORITHMS FOR CONVEX OPTIMIZATION PROBLEMS WITH NON-SEPARABLE L1-REGULARIZATION (opens in a new tab)

  9. Saddle Avoidance, Asymptotic Normality, and Exponential Acceleration in Nonsmooth Optimization

    Optimization-based algorithms are the foundation for empirically successful methods in modern fields, such as artificial intelligence and data science. Although classical optimization theory provides guarantees for functions with smoothness or convexity, a significant portion of modern problems do …

    cornell Repository record for Saddle Avoidance, Asymptotic Normality, and Exponential Acceleration in Nonsmooth Optimization (opens in a new tab)

  10. On the Relationship between Conjugate Gradient and Optimal First-Order Methods for Convex Optimization

    … and Yudin, and later extended by Nesterov, first-order algorithms for unconstrained minimization with optimal theoretical complexity bound have been proposed. On the other hand, conjugate gradient algorithms as one of the widely used first-order techniques suffer from the lack of a finite …

    waterloo Repository record for On the Relationship between Conjugate Gradient and Optimal First-Order Methods for Convex Optimization (opens in a new tab)

  11. Stochastic Methods in Model Estimation: New Algorithms and New Properties

    We study the properties of applying stochastic algorithms to solve optimization problems in model estimation. In particular, we investigate the statistical properties of estimators that are based on some stochastic algorithms in Chapters 2, 3, 4, and 5; we propose a new stochastic algorithm and …

    gatech Repository record for Stochastic Methods in Model Estimation: New Algorithms and New Properties (opens in a new tab)

  12. Structure and complexity in non-convex and non-smooth optimization

    … subject broadly seeks to both develop efficient algorithms and establish limitations on efficiencies of any algorithm for the problem class. Classical complexity theory based on oracle models targets problems that are both smooth and convex. Without smoothness, methods rely on exploiting the …

    washington Repository record for Structure and complexity in non-convex and non-smooth optimization (opens in a new tab)

  13. Solving Ellipsoidal Inclusion And Optimal Experimental Design Problems: Theory And Algorithms.

    … the development and analysis of Frank-Wolfe type algorithms for two problems, namely the ellipsoidal inclusion problem of optimization and the optimal experimental design problem of statistics. These two problems are closely related to each other and can be solved simultaneously as discussed in …

    cornell Repository record for Solving Ellipsoidal Inclusion And Optimal Experimental Design Problems: Theory And Algorithms. (opens in a new tab)

  14. Polynomial optimization: structures, algorithms, and engineering applications

    … a systematic study of polynomial optimization. First, we study the structures of various polynomial functions, based on which efficient algorithms will consequently be developed. The newly developed solution methods will be tested on a variety of engineering applications. Specifically, we first …

    umn Repository record for Polynomial optimization: structures, algorithms, and engineering applications (opens in a new tab)

  15. Efficient algorithms for simple bilevel optimization : from convex to non-convex

    … problem. This dissertation develops efficient first-order algorithms for simple bilevel optimization in both convex and nonconvex settings, with an emphasis on provable convergence and tight complexity guarantees. A unifying theme of this work is the use of cutting-plane–based approximations of …

    texas Repository record for Efficient algorithms for simple bilevel optimization : from convex to non-convex (opens in a new tab)

  16. Non-convex and Interactive Learning via Stochastic Optimization

    … stochastic optimization problem and using simple first-order algorithms like Stochastic Gradient Descent (SGD) to solve them. In the first part of the thesis, I will discuss my work on understanding why SGD succeeds in solving high-dimensional stochastic non-convex optimization problems arising in …

    cornell Repository record for Non-convex and Interactive Learning via Stochastic Optimization (opens in a new tab)

  17. New Accelerated Methods for Optimization and Reinforcement Learning

    First-order methods are widely used to tackle modern data science and machine learning problems. In this thesis, we focus on the design and analysis of novel accelerated first-order algorithms for large-scale nonlinear and stochastic optimization, addressing key challenges such as stochasticity, …

    gatech Repository record for New Accelerated Methods for Optimization and Reinforcement Learning (opens in a new tab)

  18. First-order methods of solving nonconvex optimization problems: Algorithms, convergence, and optimality

    <p>First-order methods for solving large scale nonconvex problems have been applied in many areas of machine learning, such as matrix factorization, dictionary learning, matrix sensing/completion, training deep neural networks, etc. For example, matrix factorization problems have lots of important …

    iastate Repository record for First-order methods of solving nonconvex optimization problems: Algorithms, convergence, and optimality (opens in a new tab)

  19. Efficient Methods for Hierarchical Optimization Problems: Saddle Point, Misspecified, and Bilevel

    … this dissertation studies three structures. The first is the saddle point, or min-max, structure, in which a minimizing and a maximizing player interact through a shared objective, and which appears in the formulation of every chapter. The second is the misspecified structure, in which an …

    arizona-thes Repository record for Efficient Methods for Hierarchical Optimization Problems: Saddle Point, Misspecified, and Bilevel (opens in a new tab)

  20. Low-Order Optimization Algorithms: Iteration Complexity and Applications

    … become the new norms to evaluate optimization algorithms in the modern era of big data analytics. Despite its superior local convergence property, second or higher-order methods are often disadvantaged when dealing with large-scale problems arising from machine learning. The reason for this is …

    umn Repository record for Low-Order Optimization Algorithms: Iteration Complexity and Applications (opens in a new tab)

Page 1 of 2