中文
相关论文

相关论文: Enhancing Convergence of Decentralized Gradient Tr…

200 篇论文

We study distributed multiagent optimization over (directed, time-varying) graphs. We consider the minimization of $F+G$ subject to convex constraints, where $F$ is the smooth strongly convex sum of the agent's losses and $G$ is a nonsmooth…

最优化与控制 · 数学 2020-10-13 Ying Sun , Amir Daneshmand , Gesualdo Scutari

We investigate an inertial algorithm of gradient type in connection with the minimization of a nonconvex differentiable function. The algorithm is formulated in the spirit of Nesterov's accelerated convex gradient method. We show that the…

泛函分析 · 数学 2018-11-26 Szilárd Csaba László

In this paper, we focus on solving the decentralized optimization problem of minimizing the sum of $n$ objective functions over a multi-agent network. The agents are embedded in an undirected graph where they can only send/receive…

最优化与控制 · 数学 2024-04-23 Zhuoqing Song , Lei Shi , Shi Pu , Ming Yan

Nonconvex-nonconcave minimax optimization has gained widespread interest over the last decade. However, most existing works focus on variants of gradient descent-ascent (GDA) algorithms, which are only applicable to smooth nonconvex-concave…

最优化与控制 · 数学 2025-01-17 Jiajin Li , Linglingzhi Zhu , Anthony Man-Cho So

We investigate an inertial algorithm of gradient type in connection with the minimization of a nonconvex differentiable function. The algorithm is formulated in the spirit of Nesterov's accelerated convex gradient method. We prove some…

泛函分析 · 数学 2020-02-11 Szilárd Csaba László

Gradient tracking (GT) is an algorithm designed for solving decentralized optimization problems over a network (such as training a machine learning model). A key feature of GT is a tracking mechanism that allows to overcome data…

最优化与控制 · 数学 2023-01-05 Yue Liu , Tao Lin , Anastasia Koloskova , Sebastian U. Stich

We consider a variable metric linesearch based proximal gradient method for the minimization of the sum of a smooth, possibly nonconvex function plus a convex, possibly nonsmooth term. We prove convergence of this iterative algorithm to a…

数值分析 · 数学 2017-04-11 Silvia Bonettini , Ignace Loris , Federica Porta , Marco Prato , Simone Rebegoldi

In this paper, we study the convergence properties of the Stochastic Gradient Descent (SGD) method for finding a stationary point of a given objective function $J(\cdot)$. The objective function is not required to be convex. Rather, our…

机器学习 · 统计学 2024-09-24 Rajeeva L. Karandikar , M. Vidyasagar

In this paper, we study decentralized online stochastic non-convex optimization over a network of nodes. Integrating a technique called gradient tracking in decentralized stochastic gradient descent, we show that the resulting algorithm,…

最优化与控制 · 数学 2021-04-21 Ran Xin , Usman A. Khan , Soummya Kar

We study a generic class of decentralized algorithms in which $N$ agents jointly optimize the non-convex objective $f(u):=1/N\sum_{i=1}^{N}f_i(u)$, while only communicating with their neighbors. This class of problems has become popular in…

最优化与控制 · 数学 2020-06-23 Mingyi Hong , Siliang Zeng , Junyu Zhang , Haoran Sun

We consider a composite optimization problem where the sum of a continuously differentiable and a merely lower semicontinuous function has to be minimized. The proximal gradient algorithm is the classical method for solving such a problem…

最优化与控制 · 数学 2023-05-01 Xiaoxi Jia , Christian Kanzow , Patrick Mehlitz

This paper focuses on the decentralized optimization (minimization and saddle point) problems with objective functions that satisfy Polyak-{\L}ojasiewicz condition (PL-condition). The first part of the paper is devoted to the minimization…

最优化与控制 · 数学 2024-05-14 Ilya Kuruzov , Mohammad Alkousa , Fedor Stonyakin , Alexander Gasnikov

We propose a novel analysis framework for non-descent-type optimization methodologies in nonconvex scenarios based on the Kurdyka-Lojasiewicz property. Our framework allows covering a broad class of algorithms, including those commonly…

最优化与控制 · 数学 2024-06-05 Junwen Qiu , Bohao Ma , Xiao Li , Andre Milzarek

This paper addresses the generalized descent algorithm (DEAL) for minimizing smooth functions, which is analyzed under the Kurdyka-{\L}ojasiewicz (KL) inequality. In particular, the suggested algorithm guarantees a sufficient decrease by…

最优化与控制 · 数学 2025-11-14 Masoud Ahookhosh , Susan Ghaderi , Alireza Kabgani , Morteza Rahimi

The purpose of this paper is to extend the full convergence results of the classic GLL-type (Grippo-Lampariello-Lucidi) nonmonotone methods to nonconvex and nonsmooth optimization. We propose a novel iterative framework for the minimization…

最优化与控制 · 数学 2025-04-16 Yitian Qian , Ting Tao , Shaohua Pan , Houduo Qi

We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka--\L ojaziewicz (KL) inequality we establish new convergence rates…

最优化与控制 · 数学 2016-09-14 Patrick R. Johnstone , Pierre Moulin

We study the complexity of finding the global solution to stochastic nonconvex optimization when the objective function satisfies global Kurdyka-Lojasiewicz (KL) inequality and the queries from stochastic gradient oracles satisfy mild…

最优化与控制 · 数学 2022-10-05 Ilyas Fatkhullin , Jalal Etesami , Niao He , Negar Kiyavash

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

This paper proposes a novel CTA (Combine-Then-Adapt)-based decentralized algorithm for solving convex composite optimization problems over undirected and connected networks. The local loss function in these problems contains both smooth and…

最优化与控制 · 数学 2023-03-07 Luyao Guo , Xinli Shi , Jinde Cao , Zihao Wang

We consider decentralized machine learning over a network where the training data is distributed across $n$ agents, each of which can compute stochastic model updates on their local data. The agent's common goal is to find a model that…

分布式、并行与集群计算 · 计算机科学 2022-02-09 Anastasia Koloskova , Tao Lin , Sebastian U. Stich
‹ 上一页 1 2 3 10 下一页 ›