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 94 for “"First-order methods"”.

  1. First-order methods for structured optimization

    First-order methods are gaining substantial interest in the past two decades because of their superior performance in solving today's large-scale problems. In this thesis, we study some widely used first-order methods for problems that satisfy certain structures. Specifically, in the first part, we …

    ubc Repository record for First-order methods for structured optimization (opens in a new tab) Download PDF for First-order methods for structured optimization (opens in a new tab)

  2. Novel first-order methods for bilevel and minimax optimization.

    … and bilevel optimization and develops novel first-order methods with strong theoretical guarantees for solving both classes of problems. Specifically, we study a class of constrained minimax problems and propose efficient augmented Lagrangian methods with complexity guarantees for both …

    umn Repository record for Novel first-order methods for bilevel and minimax optimization. (opens in a new tab)

  3. Efficient learning of temporal dynamics with first-order methods

    … efficient, by harnessing the power of first-order optimization methods. In particular, we provide solutions to the above challenges, by developing the following distinct, yet closely related algorithms: • First, we introduce an online learning framework for nonparametric maximum …

    uiuc Repository record for Efficient learning of temporal dynamics with first-order methods (opens in a new tab)

  4. Theory and Results on Restarting Schemes for Accelerated First Order Methods

    … problems are abundant in industry, and first order methods to solve them are growing in popularity as the size of variables reaches billions. Since the objective function could be possibly non-smooth, proximal gradient methods are one of the main tools for these problems. These methods …

    waterloo Repository record for Theory and Results on Restarting Schemes for Accelerated First Order Methods (opens in a new tab)

  5. Lyapunov analyses for first-order methods : Theory, automation, and algorithm design

    … and computer-aided analyses and design of first-order methods. The first two papers focus on developing new methodologies, while the remaining two apply these techniques to refine complexity and convergence results, as well as to design new methods. A central theme of the work is the use of …

    lund Repository record for Lyapunov analyses for first-order methods : Theory, automation, and algorithm design (opens in a new tab) Download PDF for Lyapunov analyses for first-order methods : Theory, automation, and algorithm design (opens in a new tab)

  6. Accelerated Inexact First-Order Methods for Solving Nonconvex Composite Optimization Problems

    … developing and analyzing accelerated and inexact first-order methods for solving or finding stationary points of various nonconvex composite optimization (NCO) problems. Our main tools mainly come from variational and convex analysis, and our key results are in the form of iteration complexity …

    gatech Repository record for Accelerated Inexact First-Order Methods for Solving Nonconvex Composite Optimization Problems (opens in a new tab)

  7. Fast First-Order Methods for Large-Scale Nonconvex Optimization and Semidefinite Programming

    This thesis presents fast and efficient first-order methods, with provable complexity bounds, for solving unconstrained convex/strongly convex composite optimization problems, linearly-constrained nonconvex composite optimization problems, and semidefinite programs. We show through extensive …

    gatech Repository record for Fast First-Order Methods for Large-Scale Nonconvex Optimization and Semidefinite Programming (opens in a new tab)

  8. 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)

  9. Optimal First Order Methods for Reducing Gradient Norm in Unconstrained Convex Smooth Optimization

    … thesis, we focus on convergence performance of first-order methods to compute an $\epsilon$-approximate solution of minimizing convex smooth function $f$ at the $N$-th iteration. In our introduction of the above research question, we first introduce the gradient descent method with constant step …

    clemson Repository record for Optimal First Order Methods for Reducing Gradient Norm in Unconstrained Convex Smooth Optimization (opens in a new tab)

  10. Worst Case Datasets for Solving Binary Logistic Regression via Deterministic First-Order Methods

    … regression datasets for any deterministic first order methods. We show that our datasets require at least $\cO(1/\sqrt{\varepsilon})$ first-order oracle inquires to obtain a $\varepsilon-$approximate solution under the assumption that the problem dimension is sufficiently large. Using our …

    clemson Repository record for Worst Case Datasets for Solving Binary Logistic Regression via Deterministic First-Order Methods (opens in a new tab)

  11. Theory and applications of first-order methods for convex optimization with function constraints

    … focuses on the development of efficient first-order methods for function constrained convex optimization and their applications in a few different areas, including healthcare, finance and machine learning. The thesis consists of three major studies. The first part of the thesis considers …

    gatech Repository record for Theory and applications of first-order methods for convex optimization with function constraints (opens in a new tab)

  12. FIRST-ORDER METHODS FOR NONSMOOTH NONCONVEX FUNCTIONAL CONSTRAINED OPTIMIZATION WITH OR WITHOUT SLATER POINTS

    … settings. In this paper, we show a simple first-order method finds a feasible, ϵ-stationary point at a convergence rate of O(ϵ−4) without relying on compactness or Constraint Qualification (CQ). When CQ holds, this convergence is measured by approximately satisfying the Karush-Kuhn-Tucker …

    jhu Repository record for FIRST-ORDER METHODS FOR NONSMOOTH NONCONVEX FUNCTIONAL CONSTRAINED OPTIMIZATION WITH OR WITHOUT SLATER POINTS (opens in a new tab)

  13. 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)

  14. High-Dimensional Analysis of the Linear-Quadratic Regulator Problem Using First Order Methods on GPU

    … examine the discrete-time LQR in the context of first order methods. These gradient-based methods provide an advantage in that they can be parallelized and run on GPUs. Multiple gradient-based algorithms will be proposed, and their performance will be compared with the traditional solutions for …

    tamu Repository record for High-Dimensional Analysis of the Linear-Quadratic Regulator Problem Using First Order Methods on GPU (opens in a new tab)

  15. On Variance Reduction in Machine Learning

    … SVRG, SARAH, and their BB variants are first reexamined through an `estimate sequence' lens to enable new averaging methods that tighten their convergence rates theoretically, and improve their performance empirically when the step size or the inner loop length is chosen large. Then a …

    umn Repository record for On Variance Reduction in Machine Learning (opens in a new tab)

Page 1 of 5