中文
相关论文

相关论文: Adaptive Newton-CG methods with global and local a…

200 篇论文

Recently, there has been a surge of interest in designing variants of the classical Newton-CG in which the Hessian of a (strongly) convex function is replaced by suitable approximations. This is mainly motivated by large-scale finite-sum…

最优化与控制 · 数学 2022-06-14 Yang Liu , Fred Roosta

This paper proposes and develops new Newton-type methods to solve structured nonconvex and nonsmooth optimization problems with justifying their fast local and global convergence by means of advanced tools of variational analysis and…

最优化与控制 · 数学 2026-03-03 Pham Duy Khanh , Boris S. Mordukhovich , Vo Thanh Phat

For solving large-scale non-convex problems, we propose inexact variants of trust region and adaptive cubic regularization methods, which, to increase efficiency, incorporate various approximations. In particular, in addition to approximate…

最优化与控制 · 数学 2018-02-21 Zhewei Yao , Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

Recently, a Riemannian proximal Newton method has been developed for optimizing problems in the form of $\min_{x\in\mathcal{M}} f(x) + \mu \|x\|_1$, where $\mathcal{M}$ is a compact embedded submanifold and $f(x)$ is smooth. Although this…

最优化与控制 · 数学 2025-03-25 Wen Huang , Wutao Si

In this paper, we consider a strongly convex finite-sum minimization problem over a decentralized network and propose a communication-efficient decentralized Newton's method for solving it. We first apply dynamic average consensus (DAC) so…

最优化与控制 · 数学 2022-10-04 Huikang Liu , Jiaojiao Zhang , Anthony Man-Cho So , Qing Ling

We extend the standard notion of self-concordance to non-convex optimization and develop a family of second-order algorithms with global convergence guarantees. In particular, two function classes -- \textit{weakly self-concordant}…

最优化与控制 · 数学 2026-04-07 Donald Goldfarb , Lexiao Lai , Tianyi Lin , Jiayu Zhang

In this paper we consider finding an approximate second-order stationary point (SOSP) of nonconvex conic optimization that minimizes a twice differentiable function over the intersection of an affine subspace and a convex cone. In…

最优化与控制 · 数学 2022-10-12 Chuan He , Zhaosong Lu

The cubic regularized Newton method of Nesterov and Polyak has become increasingly popular for non-convex optimization because of its capability of finding an approximate local solution with second-order guarantee. Several recent works…

最优化与控制 · 数学 2018-11-29 Junyu Zhang , Lin Xiao , Shuzhong Zhang

The Hessian-vector product has been utilized to find a second-order stationary solution with strong complexity guarantee (e.g., almost linear time complexity in the problem's dimensionality). In this paper, we propose to further reduce the…

最优化与控制 · 数学 2017-10-03 Mingrui Liu , Tianbao Yang

In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference…

最优化与控制 · 数学 2023-09-06 Nikita Doikov , Geovani Nunes Grapiglia

In this paper we consider finding an approximate second-order stationary point (SOSP) of general nonconvex conic optimization that minimizes a twice differentiable function subject to nonlinear equality constraints and also a convex conic…

最优化与控制 · 数学 2024-09-02 Chuan He , Heng Huang , Zhaosong Lu

In this paper, we study the iteration complexity of cubic regularization of Newton method for solving composite minimization problems with uniformly convex objective. We introduce the notion of second-order condition number of a certain…

最优化与控制 · 数学 2021-05-21 Nikita Doikov , Yurii Nesterov

This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general…

机器学习 · 计算机科学 2017-12-07 Nilesh Tripuraneni , Mitchell Stern , Chi Jin , Jeffrey Regier , Michael I. Jordan

This paper presents active-set methods for minimizing nonconvex twice-continuously differentiable functions subject to bound constraints. Within the faces of the feasible set, we employ descent methods with Armijo line search, utilizing…

最优化与控制 · 数学 2025-08-29 Ernesto G. Birgin , Geovani N. Grapiglia , Diaulas S. Marcondes

We study the composite convex optimization problems with a Quasi-Self-Concordant smooth component. This problem class naturally interpolates between classic Self-Concordant functions and functions with Lipschitz continuous Hessian.…

最优化与控制 · 数学 2023-08-29 Nikita Doikov

Machine learning problems such as neural network training, tensor decomposition, and matrix factorization, require local minimization of a nonconvex function. This local minimization is challenged by the presence of saddle points, of which…

最优化与控制 · 数学 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro

In this paper, a globally convergent Newton-type proximal gradient method is developed for composite multi-objective optimization problems where each objective function can be represented as the sum of a smooth function and a nonsmooth…

最优化与控制 · 数学 2024-10-25 Md Abu Talhamainuddin Ansary

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 $f$…

最优化与控制 · 数学 2023-11-09 Ruyu Liu , Shaohua Pan , Yuqia Wu , Xiaoqi Yang

This paper proposes two proximal Newton-CG methods for convex nonsmooth optimization problems in composite form. The algorithms are based on a a reformulation of the original nonsmooth problem as the unconstrained minimization of a…

最优化与控制 · 数学 2014-03-03 Panagiotis Patrinos , Lorenzo Stella , Alberto Bemporad

In this paper we consider finding a second-order stationary point (SOSP) of nonconvex equality constrained optimization when a nearly feasible point is known. In particular, we first propose a new Newton-CG method for finding an approximate…

最优化与控制 · 数学 2023-01-10 Chuan He , Zhaosong Lu , Ting Kei Pong