中文
相关论文

相关论文: On the Convergence of Primal-Dual Proximal Increme…

200 篇论文

We generalize the well-known primal-dual algorithm proposed by Chambolle and Pock for saddle point problems, and improve the condition for ensuring its convergence. The improved convergence-guaranteeing condition is effective for the…

最优化与控制 · 数学 2021-12-02 Bingsheng He , Feng Ma , Shengjie Xu , Xiaoming Yuan

The study of nonconvex minimax games has gained significant momentum in machine learning and decision science communities due to their fundamental connections to adversarial training scenarios. This work develops a primal-dual alternating…

最优化与控制 · 数学 2025-06-25 Huiling Zhang , Zi Xu , Yu-Hong Dai

The Chambolle-Pock method, also known as the primal-dual hybrid gradient method, is a standard first-order algorithm for convex-concave saddle-point problems and composite convex optimization involving two proper, lower semicontinuous,…

最优化与控制 · 数学 2026-04-09 Manu Upadhyaya

In this paper, we minimize the self-centered smoothed gap, a recently introduced optimality measure, in order to solve convex-concave saddle point problems. The self-centered smoothed gap can be computed as the sum of a convex, possibly…

最优化与控制 · 数学 2025-11-06 Olivier Fercoq

First-order primal-dual methods are appealing for their low memory overhead, fast iterations, and effective parallelization. However, they are often slow at finding high accuracy solutions, which creates a barrier to their use in…

最优化与控制 · 数学 2023-12-05 David Applegate , Oliver Hinder , Haihao Lu , Miles Lubin

We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorithm, even on the most simple problems. We thus introduce the…

最优化与控制 · 数学 2023-04-25 Olivier Fercoq

We propose two variants of the Primal Dual Hybrid Gradient (PDHG) algorithm for saddle point problems with block decomposable duals, hereafter called Multi-Timescale PDHG (MT-PDHG) and its accelerated variant (AMT-PDHG). Through novel…

最优化与控制 · 数学 2026-04-03 Junhui Zhang , Patrick Jaillet

We develop a novel primal-dual algorithm to solve a class of nonsmooth and nonlinear compositional convex minimization problems, which covers many existing and brand-new models as special cases. Our approach relies on a combination of a new…

最优化与控制 · 数学 2021-04-20 Yuzixuan Zhu , Deyi Liu , Quoc Tran-Dinh

In this paper we propose a randomized primal-dual proximal block coordinate updating framework for a general multi-block convex optimization model with coupled objective function and linear constraints. Assuming mere convexity, we establish…

最优化与控制 · 数学 2017-01-25 Xiang Gao , Yangyang Xu , Shuzhong Zhang

Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we…

最优化与控制 · 数学 2023-09-12 Morteza Boroun , Zeinab Alizadeh , Afrooz Jalilzadeh

The Primal-Dual (PD) algorithm is widely used in convex optimization to determine saddle points. While the stability of the PD algorithm can be easily guaranteed, strict contraction is nontrivial to establish in most cases. This work…

最优化与控制 · 数学 2018-11-21 Hung D. Nguyen , Thanh Long Vu , Konstantin Turitsyn , Jean-Jacques Slotine

Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning. In this paper, we propose a new stochastic primal-dual method to solve this class of problems. Different from existing methods,…

最优化与控制 · 数学 2018-11-06 Conghui Tan , Tong Zhang , Shiqian Ma , Ji Liu

In this paper, a projected primal-dual gradient flow of augmented Lagrangian is presented to solve convex optimization problems that are not necessarily strictly convex. The optimization variables are restricted by a convex set with…

最优化与控制 · 数学 2018-10-31 Han Zhang , Jieqiang Wei , Peng Yi , Xiaoming Hu

We propose and analyze a general framework called nonlinear preconditioned primal-dual with projection for solving nonconvex-nonconcave and non-smooth saddle-point problems. The framework consists of two steps. The first is a nonlinear…

最优化与控制 · 数学 2024-01-11 Lu Zhang , Hongxia Wang , Hui Zhang

The primal-dual algorithm recently proposed by Chambolle & Pock (abbreviated as CPA) for structured convex optimization is very efficient and popular. It was shown by Chambolle & Pock in \cite{CP11} and also by Shefi & Teboulle in…

最优化与控制 · 数学 2014-09-11 Raymond H. Chan , Shiqian Ma , Junfeng Yang

We study convex-concave saddle point problems with bilinear coupling, covering linearly constrained convex optimization and more general nonsmooth or constrained models via a proximable term in the dual objective. In linearly convergent…

最优化与控制 · 数学 2026-03-02 Meng Li , Paul Grigas

We study acceleration and preconditioning strategies for a class of Douglas-Rachford methods aiming at the solution of convex-concave saddle-point problems associated with Fenchel-Rockafellar duality. While the basic iteration converges…

最优化与控制 · 数学 2016-04-22 Kristian Bredies , Hongpeng Sun

In this paper, we propose a new primal-dual algorithm for minimizing $f(x) + g(x) + h(Ax)$, where $f$, $g$, and $h$ are proper lower semi-continuous convex functions, $f$ is differentiable with a Lipschitz continuous gradient, and $A$ is a…

最优化与控制 · 数学 2018-01-30 Ming Yan

Conic optimization is the minimization of a differentiable convex objective function subject to conic constraints. We propose a novel primal-dual first-order method for conic optimization, named proportional-integral projected gradient…

最优化与控制 · 数学 2021-12-15 Yue Yu , Purnanand Elango , Ufuk Topcu , Behçet Açıkmeşe

We consider a wide range of regularized stochastic minimization problems with two regularization terms, one of which is composed with a linear function. This optimization model abstracts a number of important applications in artificial…

机器学习 · 计算机科学 2018-02-02 Tianyi Lin , Linbo Qiao , Teng Zhang , Jiashi Feng , Bofeng Zhang