中文
相关论文

相关论文: On the convergence of decentralized gradient desce…

200 篇论文

In this paper, we consider the decentralized gradinet descent (DGD) given by \begin{equation*} x_i (t+1) = \sum_{j=1}^m w_{ij} x_j (t) - \alpha (t) \nabla f_i (x_i (t)). \end{equation*} We find a sharp range of the stepsize $\alpha (t)>0$…

最优化与控制 · 数学 2023-03-13 Woocheol Choi

In this paper, we establish new convergence results for the quantized distributed gradient descent and suggest a novel strategy of choosing the stepsizes for the high-performance of the algorithm. Under the strongly convexity assumption on…

最优化与控制 · 数学 2023-07-03 Woocheol Choi , Myeong-Su Lee

In this work, we are concerned with the decentralized optimization problem: \begin{equation*} \min_{x \in \Omega}~f(x) = \frac{1}{n} \sum_{i=1}^n f_i (x), \end{equation*} where $\Omega \subset \mathbb{R}^d$ is a convex domain and each $f_i…

最优化与控制 · 数学 2024-05-14 Woocheol Choi , Jimyeong Kim

Consider the consensus problem of minimizing $f(x)=\sum_{i=1}^n f_i(x)$ where each $f_i$ is only known to one individual agent $i$ out of a connected network of $n$ agents. All the agents shall collaboratively solve this problem and obtain…

最优化与控制 · 数学 2016-10-13 Kun Yuan , Qing Ling , Wotao Yin

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

最优化与控制 · 数学 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson

The paper considers distributed stochastic optimization over randomly switching networks, where agents collaboratively minimize the average of all agents' local expectation-valued convex cost functions. Due to the stochasticity in gradient…

最优化与控制 · 数学 2022-04-07 Jinlong Lei , Peng Yi , Jie Chen , Yiguang Hong

A prevalent belief among optimization specialists is that linear convergence of gradient descent is contingent on the function growing quadratically away from its minimizers. In this work, we argue that this belief is inaccurate. We show…

最优化与控制 · 数学 2025-11-11 Damek Davis , Dmitriy Drusvyatskiy , Liwei Jiang

Distributed optimization has recieved a lot of interest due to its wide applications in various fields. It consists of multiple agents that connected by a graph and optimize a total cost in a collaborative way. Often in the applications,…

最优化与控制 · 数学 2025-04-17 Woocheol Choi , Doheon Kim , Seok-Bae Yun

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

机器学习 · 统计学 2019-02-28 Xiaoyu Li , Francesco Orabona

We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing decentralized methods generally hinges on an apriori, proper…

最优化与控制 · 数学 2025-08-01 Ilya Kuruzov , Xiaokai Chen , Gesualdo Scutari , Alexander Gasnikov

In this report, we study decentralized stochastic optimization to minimize a sum of smooth and strongly convex cost functions when the functions are distributed over a directed network of nodes. In contrast to the existing work, we use…

机器学习 · 计算机科学 2020-07-24 Muhammad I. Qureshi , Ran Xin , Soummya Kar , Usman A. Khan

A generalized conditional gradient method for minimizing the sum of two convex functions, one of them differentiable, is presented. This iterative method relies on two main ingredients: First, the minimization of a partially linearized…

最优化与控制 · 数学 2021-10-01 Karl Kunisch , Daniel Walter

The gradient-push algorithm is a fundamental algorithm for the distributed optimization problem \begin{equation} \min_{x \in \mathbb{R}^d} f(x) = \sum_{j=1}^n f_j (x), \end{equation} where each local cost $f_j$ is only known to agent $a_i$…

最优化与控制 · 数学 2024-07-19 Hyogi Choi , Woocheol Choi , Gwangil Kim

A variant of consensus based distributed gradient descent (\textbf{DGD}) is studied for finite sums of smooth but possibly non-convex functions. In particular, the local gradient term in the fixed step-size iteration of each agent is…

最优化与控制 · 数学 2026-05-27 Lei Qin , Michael Cantoni , Ye Pu

This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms. Specifically, the smooth and nonsmooth terms are dealt with by gradient and…

最优化与控制 · 数学 2021-02-02 Zhi Li , Wei Shi , Ming Yan

We propose a general framework for distributed stochastic optimization under delayed gradient models. In this setting, $n$ local agents leverage their own data and computation to assist a central server in minimizing a global objective…

最优化与控制 · 数学 2026-03-04 Xinran Zheng , Tara Javidi , Behrouz Touri

In this paper, we consider minimizing a sum of local convex objective functions in a distributed setting, where the cost of communication and/or computation can be expensive. We extend and generalize the analysis for a class of nested…

最优化与控制 · 数学 2021-09-01 Albert S. Berahas , Raghu Bollapragada , Ermin Wei

This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that allows gradient descent to achieve…

机器学习 · 计算机科学 2024-12-10 Zihan Zhang , Jason D. Lee , Simon S. Du , Yuxin Chen

Based on a result by Taylor, Hendrickx, and Glineur (J. Optim. Theory Appl., 178(2):455--476, 2018) on the attainable convergence rate of gradient descent for smooth and strongly convex functions in terms of function values, an elementary…

最优化与控制 · 数学 2022-03-25 André Uschmajew , Bart Vandereycken

In this work, we establish convergence results for the distributed proximal point algorithm (DPPA) for distributed optimization problems. We consider the problem on the whole domain Rd and find a general condition on the stepsize and cost…

最优化与控制 · 数学 2023-07-11 Woocheol Choi
‹ 上一页 1 2 3 10 下一页 ›