中文
相关论文

相关论文: Block Coordinate Descent Methods for Structured No…

200 篇论文

We consider distributed optimization over networks where each agent is associated with a smooth and strongly convex local objective function. We assume that the agents only have access to unbiased estimators of the gradient of their…

最优化与控制 · 数学 2021-10-14 Farzad Yousefian , Jayesh Yevale , Harshal D. Kaushik

The stochastic gradient descent has been widely used for solving composite optimization problems in big data analyses. Many algorithms and convergence properties have been developed. The composite functions were convex primarily and…

机器学习 · 统计学 2020-03-03 Takayuki Kawashima , Hironori Fujisawa

We study distributed big-data nonconvex optimization in multi-agent networks. We consider the (constrained) minimization of the sum of a smooth (possibly) nonconvex function, i.e., the agents' sum-utility, plus a convex (possibly) nonsmooth…

最优化与控制 · 数学 2018-09-03 Ivano Notarnicola , Ying Sun , Gesualdo Scutari , Giuseppe Notarstefano

Distributed optimization advances centralized machine learning methods by enabling parallel and decentralized learning processes over a network of computing nodes. This work provides an accelerated consensus-based distributed algorithm for…

系统与控制 · 电气工程与系统科学 2025-07-01 Mohammadreza Doostmohammadian , Hamid R. Rabiee

We consider approaches for improving the efficiency of algorithms for fitting nonconvex penalized regression models such as SCAD and MCP in high dimensions. In particular, we develop rules for discarding variables during cyclic coordinate…

统计计算 · 统计学 2016-07-20 Sangin Lee , Patrick Breheny

In this paper, we investigate the non-asymptotic stationary convergence behavior of Stochastic Mirror Descent (SMD) for nonconvex optimization. We focus on a general class of nonconvex nonsmooth stochastic optimization problems, in which…

最优化与控制 · 数学 2018-06-14 Siqi Zhang , Niao He

Constrained clustering leverages limited domain knowledge to improve clustering performance and interpretability, but incorporating pairwise must-link and cannot-link constraints is an NP-hard challenge, making global optimization…

机器学习 · 计算机科学 2025-10-28 Pedro Chumpitaz-Flores , My Duong , Cristobal Heredia , Kaixun Hua

We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems. The method is based on the novel ECD framework of…

机器学习 · 计算机科学 2023-06-02 G. Bruno De Luca , Alice Gatti , Eva Silverstein

Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive,…

机器学习 · 计算机科学 2017-03-08 Dmytro Perekrestenko , Volkan Cevher , Martin Jaggi

Coordinate descent methods usually minimize a cost function by updating a random decision variable (corresponding to one coordinate) at a time. Ideally, we would update the decision variable that yields the largest decrease in the cost…

机器学习 · 计算机科学 2018-12-05 Farnood Salehi , Patrick Thiran , L. Elisa Celis

Many relevant problems in the area of systems and control, such as controller synthesis, observer design and model reduction, can be viewed as optimization problems involving dynamical systems: for instance, maximizing performance in the…

最优化与控制 · 数学 2023-11-15 Pascal Den Boef , Jos Maubach , Wil Schilders , Nathan van de Wouw

In this work we show that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable convex…

最优化与控制 · 数学 2013-11-27 Peter Richtárik , Martin Takáč

Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Up to a primal-dual transformation, it is also the same as accelerated stochastic gradient descent…

最优化与控制 · 数学 2016-05-30 Zeyuan Allen-Zhu , Zheng Qu , Peter Richtárik , Yang Yuan

Consensus optimization has received considerable attention in recent years. A number of decentralized algorithms have been proposed for {convex} consensus optimization. However, to the behaviors or consensus \emph{nonconvex} optimization,…

最优化与控制 · 数学 2018-01-29 Jinshan Zeng , Wotao Yin

Coordinate-type subgradient methods for addressing nonsmooth optimization problems are relatively underexplored due to the set-valued nature of the subdifferential. In this work, our study focuses on nonsmooth composite optimization…

最优化与控制 · 数学 2023-08-24 Lei Zhao , Ding Chen , Daoli Zhu , Xiao Li

Coherent Ising machines (CIMs) have emerged as specialized quantum hardware for large-scale combinatorial optimization. However, for large instances that remain challenging for classical methods, some platforms support only finite-precision…

量子物理 · 物理学 2026-03-25 Keming He , Yuehan Zhang , Hongshun Yao , Jin-Guo Liu , Xin Wang

In decentralized optimization over networks, synchronizing the updates of all nodes incurs significant communication overhead. For this reason, much of the recent literature has focused on the analysis and design of asynchronous…

We propose a new asynchronous parallel block-descent algorithmic framework for the minimization of the sum of a smooth nonconvex function and a nonsmooth convex one, subject to both convex and nonconvex constraints. The proposed framework…

最优化与控制 · 数学 2018-04-02 Loris Cannelli , Francisco Facchinei , Vyacheslav Kungurtsev , Gesualdo Scutari

Stochastic gradient descent (SGD) is a promising method for solving large-scale inverse problems, due to its excellent scalability with respect to data size. In this work, we analyze a new data-driven regularized stochastic gradient descent…

数值分析 · 数学 2024-09-30 Zehui Zhou

Control Co-Design (CCD) considers the coupled effects of both the plant and control parameters to optimize a system's closed-loop transient performance during the design stage. This paper presents a new method for CCD with guarantees on…

系统与控制 · 电气工程与系统科学 2023-10-19 Trevor J. Bird , Jacob A. Siefert , Herschel C. Pangborn , Neera Jain
‹ 上一页 1 8 9 10 下一页 ›