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 13 of 13 for “"accelerated gradient method"”.
-
Optimal First Order Methods for Reducing Gradient Norm in Unconstrained Convex Smooth Optimization
… 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 size …
-
First-Order Algorithms for Convex Smooth Optimization Problems With Homogeneous Linear Constraints
… 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 projection …
-
Generalized Accelerated Optimization Framework for Big Data Processing
… these problems can have black-box first-order methods are widely used in solving them. Among the existing firstorder methods, the ones that are most widely used are different variants of Fast Gradient Methods (FGM). Such methods are devised in the context of the estimating sequences framework …
-
Supermemory gradient method for minimizing unconstrained functions
A new accelerated gradient method for finding the minimum of a function f(x) whose variables are unconstrained is presented. The new algorithm can be stated as follows: where x is an n-vector, g(x) is the gradient of the function f(x), ox is the change in the position vector for the iteration under …
-
Method of independent multipliers for minimizing unconstrained functions
A new accelerated gradient method for finding the minimum of a function f(x) whose variables are unconstrained is presented. The new algorithm can be stated where ax is the change in the position vector x, g(x) is the gradient of the function f(x), and a and fi are scalars chosen at each step so as …
-
Métodos de otimização aplicados à estatística
… intersection between the areas of optimization methods and the statistical models. We work in this intersection in two ways. First, we take as a case study, in the field of optimization methods, the gradient descent, accelerated gradient descent, high-order accelerated gradient and …
-
Interpolation, growth conditions, and stochastic gradient descent
… the training data. In such cases, stochastic gradient descent has been shown to converge without decreasing step-sizes or averaging, and can achieve the fast convergence of deterministic gradient methods. Recent work has further shown that stochastic acceleration and line-search methods for …
-
Accelerated algorithms for composite saddle-point problems and applications
… machine learning and image processing. Two new accelerated algorithms for solving composite saddle-point problems are introduced. Due to the two-block structure of the CSP problem, it can be solved by any algorithm belonging to the block-decomposition hybrid proximal extragradient (BD-HPE) …
-
Projection-Free and Accelerated Methods for Constrained Optimization and Saddle-Points Problems
… investigates primal-dual optimization methods for solving nonconvex problems in both stochastic and deterministic settings. The proposed methods address challenges in feasibility, scalability, and computational efficiency, offering robust solutions with theoretical guarantees. In the …
-
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, …
-
Stochastic algorithms for distributed optimization and machine learning
… of optimization, in the way the latter provides methods and theory. While data tends to be collected in a distributed fashion, the standard machine learning models require centralizing the training data on one machine or in a data center, which incurs significant communication cost and puts data …
-
Block-decomposition and accelerated gradient methods for large-scale convex optimization
… this thesis, we develop block-decomposition (BD) methods and variants of accelerated *9gradient methods for large-scale conic programming and convex optimization, respectively. The BD methods, discussed in the first two parts of this thesis, are inexact versions of proximal-point methods applied …
-
Accelerated Inexact First-Order Methods for Solving Nonconvex Composite Optimization Problems
This thesis focuses on 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 …