中文
相关论文

相关论文: Proximal gradient flow and Douglas-Rachford splitt…

200 篇论文

Minimax problems have recently attracted a lot of research interests. A few efforts have been made to solve decentralized nonconvex strongly-concave (NCSC) minimax-structured optimization; however, all of them focus on smooth problems with…

最优化与控制 · 数学 2023-04-06 Yangyang Xu

This paper investigates the convex optimization problem with general convex inequality constraints. To cope with this problem, a discrete-time algorithm, called augmented primal-dual gradient algorithm (Aug-PDG), is studied and analyzed. It…

最优化与控制 · 数学 2020-11-18 Min Meng , Xiuxian Li

We adapt the Douglas-Rachford (DR) splitting method to solve nonconvex feasibility problems by studying this method for a class of nonconvex optimization problem. While the convergence properties of the method for convex problems have been…

最优化与控制 · 数学 2015-11-17 Guoyin Li , Ting Kei Pong

Non-convex functional constrained optimization problems have gained substantial attention in machine learning and data science, addressing broad requirements that typically go beyond the often performance-centric objectives. An influential…

最优化与控制 · 数学 2025-10-29 Sang Bin Moon , Jong Gwang Kim , Ashish Chandra , Christopher Brinton , Abolfazl Hashemi

The problem of minimization of the sum of two convex functions has various theoretical and real-world applications. One of the popular methods for solving this problem is the proximal gradient method (proximal forward-backward algorithm). A…

最优化与控制 · 数学 2019-11-12 Daniel Reem , Simeon Reich , Alvaro De Pierro

We develop and analyze an asynchronous algorithm for distributed convex optimization when the objective writes a sum of smooth functions, local to each worker, and a non-smooth function. Unlike many existing methods, our distributed…

最优化与控制 · 数学 2019-12-13 Konstantin Mishchenko , Franck Iutzeler , Jérôme Malick

Gradient-flow (GF) viewpoints unify and illuminate optimization algorithms, yet most GF analyses focus on unconstrained settings. We develop a geometry-respecting framework for constrained problems by (i) reparameterizing feasible sets with…

最优化与控制 · 数学 2025-08-29 Valentin Leplat

Stochastic optimization lies at the core of most statistical learning models. The recent great development of stochastic algorithmic tools focused significantly onto proximal gradient iterations, in order to find an efficient approach for…

机器学习 · 计算机科学 2020-03-31 Andrei Patrascu , Ciprian Paduraru , Paul Irofti

Motivated by nonconvex, inconsistent feasibility problems in imaging, the relaxed alternating averaged reflections algorithm, or relaxed Douglas-Rachford algorithm (DR$\lambda$), was first proposed over a decade ago. Convergence results for…

最优化与控制 · 数学 2020-03-26 D. Russell Luke , Anna-Lena Martins

In this paper, based a novel primal-dual dynamical model with adaptive scaling parameters and Bregman divergences, we propose new accelerated primal-dual proximal gradient splitting methods for solving bilinear saddle-point problems with…

最优化与控制 · 数学 2024-09-04 Hao Luo

This paper presents a non-linear stability analysis for dc-microgrids in both, interconnected mode and island operation with primary control. The proposed analysis is based on the fact that the dynamical model of the grid is a gradient…

最优化与控制 · 数学 2019-01-07 Alejandro Garces

We study the cyclic relaxed Douglas-Rachford algorithm for possibly nonconvex, and inconsistent feasibility problems. This algorithm can be viewed as a convex relaxation between the cyclic Douglas-Rachford algorithm first introduced by…

最优化与控制 · 数学 2026-05-06 Thi Lan Dinh , G. S. Matthijs Jansen , D. Russell Luke

Stochastic gradient algorithms are often unstable when applied to functions that do not have Lipschitz-continuous and/or bounded gradients. Gradient clipping is a simple and effective technique to stabilize the training process for problems…

最优化与控制 · 数学 2021-06-11 Vien V. Mai , Mikael Johansson

This paper proposes a novel technique called "successive stochastic smoothing" that optimizes nonsmooth and discontinuous functions while considering various constraints. Our methodology enables local and global optimization, making it a…

最优化与控制 · 数学 2023-08-17 Vladimir Norkin , Alois Pichler , Anton Kozyriev

In this paper, we consider a nonsmooth convex finite-sum problem with a conic constraint. To overcome the challenge of projecting onto the constraint set and computing the full (sub)gradient, we introduce a primal-dual incremental gradient…

最优化与控制 · 数学 2021-05-10 Afrooz Jalilzadeh

As a counterpoint to recent numerical methods for crystal surface evolution, which agree well with microscopic dynamics but suffer from significant stiffness that prevents simulation on fine spatial grids, we develop a new numerical method…

数值分析 · 数学 2020-06-24 Katy Craig , Jian-Guo Liu , Jianfeng Lu , Jeremy L. Marzuola , Li Wang

We consider the composite minimization problem with the objective function being the sum of a continuously differentiable and a merely lower semicontinuous and extended-valued function. The proximal gradient method is probably the most…

最优化与控制 · 数学 2024-11-20 Christian Kanzow , Leo Lehmann

In this paper, we propose an efficient and flexible algorithm to solve dynamic mean-field planning problems based on an accelerated proximal gradient method. Besides an easy-to-implement gradient descent step in this algorithm, a crucial…

最优化与控制 · 数学 2021-03-01 Jiajia Yu , Rongjie Lai , Wuchen Li , Stanley Osher

A classical approach for solving discrete time nonlinear control on a finite horizon consists in repeatedly minimizing linear quadratic approximations of the original problem around current candidate solutions. While widely popular in many…

最优化与控制 · 数学 2025-07-08 Vincent Roulet , Siddhartha Srinivasa , Maryam Fazel , Zaid Harchaoui

This paper presents a novel stochastic gradient descent algorithm for constrained optimization. The proposed algorithm randomly samples constraints and components of the finite sum objective function and relies on a relaxed logarithmic…

最优化与控制 · 数学 2025-05-13 Naum Dimitrieski , Jing Cao , Christian Ebenbauer