中文
相关论文

相关论文: Limit Behavior and the Role of Augmentation in Pro…

200 篇论文

We present a new kind of Lagrangian duality theory for set-valued convex optimization problems whose objective and constraint maps are defined between preordered normed spaces. The theory is accomplished by introducing a new set-valued…

最优化与控制 · 数学 2024-01-17 Fernando García-Castaño , M. A. Melguizo Padial

We consider the general problem of online convex optimization with time-varying additive constraints in the presence of predictions for the next cost and constraint functions. A novel primal-dual algorithm is designed by combining a…

机器学习 · 计算机科学 2022-01-11 Daron Anderson , George Iosifidis , Douglas J. Leith

We are interested in solving convex optimization problems with large numbers of constraints. Randomized algorithms, such as random constraint sampling, have been very successful in giving nearly optimal solutions to such problems. In this…

最优化与控制 · 数学 2016-11-29 William B. Haskell , Yu Pengqian

In this paper, we explore a broad class of constrained saddle point problems with a bilevel structure, wherein the upper-level objective function is nonconvex-concave and smooth over compact and convex constraint sets, subject to a strongly…

最优化与控制 · 数学 2025-03-31 Mohammad Mahdi Ahmadi , Erfan Yazdandoost Hamedani

The paper proposes a variational-inequality based primal-dual dynamic that has a globally exponentially stable saddle-point solution when applied to solve linear inequality constrained optimization problems. A Riemannian geometric framework…

最优化与控制 · 数学 2020-10-07 P. Bansode , V. Chinde , S. R. Wagh , R. Pasumarthy , N. M. Singh

The optimal control of a globally unstable two-dimensional separated boundary layer over a bump is considered using augmented Lagrangian optimization procedures. The present strategy allows of controlling the flow from a fully developed…

流体动力学 · 物理学 2018-03-14 Pierre-Yves Passaggia , Uwe Ehrenstein

Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of…

神经与进化计算 · 计算机科学 2022-02-23 Youssef Diouane , Aurelien Lucchi , Vihang Patil

The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier"(often unconstrained) sub-problems with respect to the original…

最优化与控制 · 数学 2020-04-16 Dusan Jakovetic , Dragana Bajovic , Joao Xavier , Jose M. F. Moura

We study a class of convex-concave saddle-point problems of the form $\min_x\max_y \langle Kx,y\rangle+f_{\cal{P}}(x)-h^\ast(y)$ where $K$ is a linear operator, $f_{\cal{P}}$ is the sum of a convex function $f$ with a Lipschitz-continuous…

最优化与控制 · 数学 2021-06-07 Vladimir Kolmogorov , Thomas Pock

In this paper, we propose the primal-dual method of multipliers (PDMM) for distributed optimization over a graph. In particular, we optimize a sum of convex functions defined over a graph, where every edge in the graph carries a linear…

分布式、并行与集群计算 · 计算机科学 2017-02-06 G. Zhang , R. Heusdens

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until…

机器学习 · 计算机科学 2023-10-26 Scott Pesme , Nicolas Flammarion

The unreal high flows may appear on the actually congested links in the result when a monotonically increasing link travel time function of flow volume is adopted in traffic assignment. The fixed link flow results of a static traffic…

系统与控制 · 电气工程与系统科学 2020-06-02 Shengxue He

Despite the non-convexity of most modern machine learning parameterizations, Lagrangian duality has become a popular tool for addressing constrained learning problems. We revisit Augmented Lagrangian methods, which aim to mitigate the…

机器学习 · 计算机科学 2025-10-30 Ignacio Boero , Ignacio Hounie , Alejandro Ribeiro

Recently, saddle point problems have received much attention due to their powerful modeling capability for a lot of problems from diverse domains. Applications of these problems occur in many applied areas, such as robust optimization,…

最优化与控制 · 数学 2022-02-15 Mohammad Alkousa , Alexander Gasnikov , Pavel Dvurechensky , Abdurakhmon Sadiev , Lama Razouk

Large-scale constrained optimization is pivotal in modern scientific, engineering, and industrial computation, often involving complex systems with numerous variables and constraints. This paper provides a unified and comprehensive…

最优化与控制 · 数学 2025-10-21 Kangkang Deng , Rui Wang , Zhenyuan Zhu , Junyu Zhang , Zaiwen Wen

We study constrained nonconvex optimization problems in machine learning, signal processing, and stochastic control. It is well-known that these problems can be rewritten to a minimax problem in a Lagrangian form. However, due to the lack…

机器学习 · 计算机科学 2019-10-29 Zhehui Chen , Xingguo Li , Lin F. Yang , Jarvis Haupt , Tuo Zhao

The paper considers distributed gradient flow (DGF) for multi-agent nonconvex optimization. DGF is a continuous-time approximation of distributed gradient descent that is often easier to study than its discrete-time counterpart. The paper…

最优化与控制 · 数学 2020-08-13 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

This work investigates the distributed constrained optimization problem under inter-agent communication delays from the perspective of passivity. First, we propose a continuous-time algorithm for distributed constrained optimization with…

最优化与控制 · 数学 2022-05-02 Mengmou Li , Shunya Yamashita , Takeshi Hatanaka , Graziano Chesi

We study convex-concave saddle point problems with bilinear coupling, covering linearly constrained convex optimization and more general nonsmooth or constrained models via a proximable term in the dual objective. In linearly convergent…

最优化与控制 · 数学 2026-03-02 Meng Li , Paul Grigas

We solve large-scale mixed-integer linear programs (MILPs) via distributed asynchronous saddle point computation. This is motivated by the MILPs being able to model problems in multi-agent autonomy, e.g., task assignment problems and…

最优化与控制 · 数学 2022-11-23 Luke Fina , Matthew Hale