English
Related papers

Related papers: KKT Conditions, First-Order and Second-Order Optim…

200 papers

The asymptotic Karush-Kuhn-Tucker (AKKT) optimality conditions are distinguished from other approaches in the literature by virtue of their capacity to be effectively derived through numerical methods, such as the utilization of an…

Optimization and Control · Mathematics 2026-05-29 Rodrigo B. Moreira , Moisés R. C. do Monte , Valeriano A. de Oliveira

In this paper we theoretically show that interior-point methods based on self-concordant barriers possess favorable global complexity beyond their standard application area of convex optimization. To do that we propose first- and…

Optimization and Control · Mathematics 2024-04-30 Pavel Dvurechensky , Mathias Staudigl

One of the most important optimality conditions to aid to solve a vector optimization problem is the first-order necessary optimality condition that generalizes the Karush-Kuhn-Tucker condition. However, to obtain the sufficient optimality…

Necessary conditions for high-order optimality in smooth nonlinear constrained optimization are explored and their inherent intricacy discussed. A two-phase minimization algorithm is proposed which can achieve approximate first-, second-…

Optimization and Control · Mathematics 2021-05-31 C. Cartis , N. I. M. Gould , Ph. L. Toint

We consider a special class of nonconvex semidefinite programming problems and show that every point satisfying the Karush--Kuhn--Tucker (KKT) conditions is globally optimal despite nonconvexity. This property is related to pseudoconvex…

Optimization and Control · Mathematics 2025-06-23 Akatsuki Nishioka , Yoshihiro Kanno

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

We study the problem of minimizing a sum of convex objective functions where the components of the objective are available at different nodes of a network and nodes are allowed to only communicate with their neighbors. The use of…

Optimization and Control · Mathematics 2015-04-24 Aryan Mokhtari , Qing Ling , Alejandro Ribeiro

This paper analyzes the contraction of the primal-dual gradient optimization via contraction theory in the context of discrete-time updating dynamics. The contraction theory based on Riemannian manifolds is first established for convergence…

Optimization and Control · Mathematics 2019-07-25 Yanxu Su , Yang Shi , Changyin Sun

This paper develops an efficient algorithm for computing the Euclidean projection onto the top-k-sum constraint, a key operation in financial risk management and matrix optimization problems. Existing projection methods rely on sorting and…

Optimization and Control · Mathematics 2025-12-12 Jianting Pan , Ming Yan

In this paper, we propose second-order sufficient optimality conditions for a very general nonconvex constrained optimization problem, which covers many prominent mathematical programs.Unlike the existing results in the literature, our…

Optimization and Control · Mathematics 2022-11-24 Matus Benko , Helmut Gfrerer , Jane Ye , Jin Zhang , Jinchuan Zhou

In this work, optimality conditions and classical results from duality theory are derived for continuous-time linear optimization problems with inequality constraints. The optimality conditions are given in the Karush-Kuhn-Tucker form. Weak…

Optimization and Control · Mathematics 2023-05-10 Valeriano Antunes de Oliveira

Estimation of the precision matrix (or inverse covariance matrix) is of great importance in statistical data analysis and machine learning. However, as the number of parameters scales quadratically with the dimension $p$, computation…

Computation · Statistics 2022-11-02 Qian LI , Binyan Jiang , Defeng Sun

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

This paper focuses on the minimization of a sum of a twice continuously differentiable function $f$ and a nonsmooth convex function. An inexact regularized proximal Newton method is proposed by an approximation to the Hessian of $f$…

Optimization and Control · Mathematics 2023-11-09 Ruyu Liu , Shaohua Pan , Yuqia Wu , Xiaoqi Yang

In recent years, the success of deep learning has inspired many researchers to study the optimization of general smooth non-convex functions. However, recent works have established pessimistic worst-case complexities for this class…

Optimization and Control · Mathematics 2020-10-28 Jikai Jin

In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ($l_1$ norm) and Chebyshev ($\max$ norm). The optimality conditions are based on neural networks with at…

Optimization and Control · Mathematics 2025-06-24 Vinesha Peiris , Nadezda Sukhorukova , Julien Ugon

We propose a variant of the classical augmented Lagrangian method for constrained optimization problems in Banach spaces. Our theoretical framework does not require any convexity or second-order assumptions and allows the treatment of…

Optimization and Control · Mathematics 2018-07-13 Christian Kanzow , Daniel Steck , Daniel Wachsmuth

Using an optimization algorithm to solve a machine learning problem is one of mainstreams in the field of science. In this work, we demonstrate a comprehensive comparison of some state-of-the-art first-order optimization algorithms for…

Machine Learning · Computer Science 2014-04-29 Yu Wei , Pock Thomas

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we…

Machine Learning · Statistics 2013-05-15 Julien Mairal

Balancing convergence speed, generalization capability, and computational efficiency remains a core challenge in deep learning optimization. First-order gradient descent methods, epitomized by stochastic gradient descent (SGD) and Adam,…