中文
相关论文

相关论文: Decentralized Saddle-Point Problems with Different…

200 篇论文

Optimizing non-convex functions is of primary importance in the vast majority of machine learning algorithms. Even though many gradient descent based algorithms have been studied, successive convex approximation based algorithms have been…

最优化与控制 · 数学 2019-03-06 Amrit Singh Bedi , Ketan Rajawat , Vaneet Aggarwal

Modern power systems are now in continuous process of massive changes. Increased penetration of distributed generation, usage of energy storage and controllable demand require introduction of a new control paradigm that does not rely on…

We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence…

机器学习 · 计算机科学 2019-09-17 Luo Luo , Cheng Chen , Yujun Li , Guangzeng Xie , Zhihua Zhang

In this paper, we investigate a class of constrained saddle point (SP) problems where the objective function is nonconvex-concave and smooth. This class of problems has wide applicability in machine learning, including robust multi-class…

最优化与控制 · 数学 2023-11-02 Morteza Boroun , Erfan Yazdandoost Hamedani , Afrooz Jalilzadeh

We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution. The local functions distributed across the nodes are assumed to…

Federated learning (FL) approaches for saddle point problems (SPP) have recently gained in popularity due to the critical role they play in machine learning (ML). Existing works mostly target smooth unconstrained objectives in Euclidean…

机器学习 · 计算机科学 2024-09-17 Site Bai , Brian Bullins

We introduce a new sequential subspace optimization method for large-scale saddle-point problems. It solves iteratively a sequence of auxiliary saddle-point problems in low-dimensional subspaces, spanned by directions derived from…

最优化与控制 · 数学 2020-08-24 Yoni Choukroun , Michael Zibulevsky , Pavel Kisilev

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

In this work, we consider a time-varying stochastic saddle point problem in which the objective is revealed sequentially, and the data distribution depends on the decision variables. Problems of this type express the distributional…

最优化与控制 · 数学 2022-12-07 Killian Wood , Emiliano Dall'Anese

In centralized settings, it is well known that stochastic gradient descent (SGD) avoids saddle points and converges to local minima in nonconvex problems. However, similar guarantees are lacking for distributed first-order algorithms. The…

最优化与控制 · 数学 2022-03-07 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

We investigate the problem of finding second-order stationary points (SOSP) in differentially private (DP) stochastic non-convex optimization. Existing methods suffer from two key limitations: (i) inaccurate convergence error rate due to…

机器学习 · 计算机科学 2026-01-21 Youming Tao , Zuyuan Zhang , Dongxiao Yu , Xiuzhen Cheng , Falko Dressler , Di Wang

We revisit the smooth convex-concave bilinearly-coupled saddle-point problem of the form $\min_x\max_y f(x) + \langle y,\mathbf{B} x\rangle - g(y)$. In the highly specific case where each of the functions $f(x)$ and $g(y)$ is either affine…

最优化与控制 · 数学 2024-11-25 Dmitry Kovalev , Ekaterina Borodich

Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to…

机器学习 · 计算机科学 2017-02-08 Armen Aghajanyan

We consider a class of non-smooth strongly convex-strongly concave saddle point problems in a decentralized setting without a central server. To solve a consensus formulation of problems in this class, we develop an inexact primal dual…

机器学习 · 计算机科学 2023-09-14 Chhavi Sharma , Vishnu Narayanan , P. Balamurugan

Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training…

机器学习 · 计算机科学 2021-03-03 Yasaman Esfandiari , Aditya Balu , Keivan Ebrahimi , Umesh Vaidya , Nicola Elia , Soumik Sarkar

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 study saddle point (SP) problems, focusing on convex-concave optimization involving functions that satisfy either two-sided quadratic functional growth (QFG) or two-sided quadratic gradient growth (QGG)--novel conditions…

最优化与控制 · 数学 2025-10-15 Cody Melcher , Afrooz Jalilzadeh , Erfan Yazdandoost Hamedani

We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network…

Methods with adaptive scaling of different features play a key role in solving saddle point problems, primarily due to Adam's popularity for solving adversarial machine learning problems, including GANS training. This paper carries out a…

机器学习 · 计算机科学 2023-06-22 Aleksandr Beznosikov , Aibek Alanov , Dmitry Kovalev , Martin Takáč , Alexander Gasnikov

Local search heuristics for non-convex optimizations are popular in applied machine learning. However, in general it is hard to guarantee that such algorithms even converge to a local minimum, due to the existence of complicated saddle…

机器学习 · 计算机科学 2016-02-19 Anima Anandkumar , Rong Ge