中文
相关论文

相关论文: Convergence Analysis of the Lion Optimizer in Cent…

200 篇论文

We consider the problem of decentralized optimization where a collection of agents, each having access to a local cost function, communicate over a time-varying directed network and aim to minimize the sum of those functions. In practice,…

系统与控制 · 电气工程与系统科学 2021-09-01 Yiyue Chen , Abolfazl Hashemi , Haris Vikalo

System identification is a fundamental problem in control and learning, particularly in high-stakes applications where data efficiency is critical. Classical approaches, such as the ordinary least squares estimator (OLS), achieve an…

系统与控制 · 电气工程与系统科学 2025-06-12 Xiong Zeng , Jing Yu , Necmiye Ozay

We propose an algorithm for distributed optimization over time-varying communication networks. Our algorithm uses an optimized ratio between the number of rounds of communication and gradient evaluations to achieve fast convergence. The…

最优化与控制 · 数学 2020-01-08 Bryan Van Scoy , Laurent Lessard

We provide the first deterministic distributed synchronizer with near-optimal time complexity and message complexity overheads. Concretely, given any distributed algorithm $\mathcal{A}$ that has time complexity $T$ and message complexity…

数据结构与算法 · 计算机科学 2023-05-12 Mohsen Ghaffari , Anton Trygub

Communication compression has become a key strategy to speed up distributed optimization. However, existing decentralized algorithms with compression mainly focus on compressing DGD-type algorithms. They are unsatisfactory in terms of…

机器学习 · 计算机科学 2021-03-22 Xiaorui Liu , Yao Li , Rongrong Wang , Jiliang Tang , Ming Yan

The training of deep vision models is fundamentally a signal recovery problem amidst high-dimensional stochastic noise. Current optimization paradigms impose a static compromise on information channel capacity. For instance, magnitude-based…

机器学习 · 计算机科学 2025-12-03 Ahmed Nebli

In this paper, we study unconstrained distributed optimization strongly convex problems, in which the exchange of information in the network is captured by a directed graph topology over digital channels that have limited capacity (and…

系统与控制 · 电气工程与系统科学 2023-09-12 Apostolos I. Rikos , Wei Jiang , Themistoklis Charalambous , Karl H. Johansson

Distributed optimization finds applications in large-scale machine learning, data processing and classification over multi-agent networks. In real-world scenarios, the communication network of agents may encounter latency that may affect…

系统与控制 · 电气工程与系统科学 2025-10-06 Mohammadreza Doostmohammadian , Narahari Kasagatta Ramesh , Alireza Aghasi

Distributed optimization finds many applications in machine learning, signal processing, and control systems. In these real-world applications, the constraints of communication networks, particularly limited bandwidth, necessitate…

系统与控制 · 电气工程与系统科学 2024-10-29 Mohammadreza Doostmohammadian , Sérgio Pequito

Distributed optimization has found widespread applications in smart grids, optimal control, and machine learning. This paper studies distributed consensus optimization. We extend the Augmented Lagrangian-based Alternating Direction Inexact…

最优化与控制 · 数学 2026-05-21 Xu Du , Jingzhe Wang , Karl H. Johansson , Apostolos I. Rikos

We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the…

机器学习 · 统计学 2025-03-14 Jordan Lekeufack , Michael I. Jordan

Dual decomposition is widely utilized in distributed optimization of multi-agent systems. In practice, the dual decomposition algorithm is desired to admit an asynchronous implementation due to imperfect communication, such as time delay…

最优化与控制 · 数学 2021-03-05 Yifan Su , Zhaojian Wang , Ming Cao , Mengshuo Jia , Feng Liu

This paper considers distributed nonconvex optimization with the cost functions being distributed over agents. Noting that information compression is a key tool to reduce the heavy communication load for distributed algorithms as agents…

最优化与控制 · 数学 2022-10-10 Xinlei Yi , Shengjun Zhang , Tao Yang , Tianyou Chai , Karl H. Johansson

In this paper, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This…

最优化与控制 · 数学 2023-08-01 Roula Nassif , Stefan Vlaski , Marco Carpentiero , Vincenzo Matta , Marc Antonini , Ali H. Sayed

We study the so-called distributed two-time-scale gradient method for solving convex optimization problems over a network of agents when the communication bandwidth between the nodes is limited, and so information that is exchanged between…

系统与控制 · 电气工程与系统科学 2021-06-01 Marcos M. Vasconcelos , Thinh T. Doan , Urbashi Mitra

We study non-convex distributed optimization problems where a set of agents collaboratively solve a separable optimization problem that is distributed over a time-varying network. The existing methods to solve these problems rely on (at…

最优化与控制 · 数学 2022-04-26 Hadi Reisizadeh , Behrouz Touri , Soheil Mohajer

We consider convex and nonconvex constrained optimization with a partially separable objective function: agents minimize the sum of local objective functions, each of which is known only by the associated agent and depends on the variables…

最优化与控制 · 数学 2020-10-20 Loris Cannelli , Francisco Facchinei , Gesualdo Scutari , Vyacheslav Kungurtsev

This paper studies the convergence properties the well-known message-passing algorithm for convex optimisation. Under the assumption of pairwise separability and scaled diagonal dominance, asymptotic convergence is established and a simple…

最优化与控制 · 数学 2019-04-10 Zhaorong Zhang , Minyue Fu

The Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) method is a cutting-edge distributed optimization algorithm known for its superior numerical performance. It relies on each agent transmitting information to a central…

系统与控制 · 电气工程与系统科学 2025-04-09 Xu Du , Xiaohua Zhou , Shijie Zhu

This paper presents a decentralized algorithm for solving distributed convex optimization problems in dynamic networks with time-varying objectives. The unique feature of the algorithm lies in its ability to accommodate a wide range of…

最优化与控制 · 数学 2023-07-12 Navneet Agrawal , Renato L. G. Cavalcante , Masahiro Yukawa , Slawomir Stanczak