中文
相关论文

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

200 篇论文

Characterizing and understanding the dynamics of stochastic gradient descent (SGD) around saddle points remains an open problem. We first show that saddle points in neural networks can be divided into two types, among which the Type-II…

机器学习 · 计算机科学 2024-07-03 Liu Ziyin , Botao Li , Tomer Galanti , Masahito Ueda

In this work, we conduct a systematic study of stochastic saddle point problems (SSP) and stochastic variational inequalities (SVI) under the constraint of $(\epsilon,\delta)$-differential privacy (DP) in both Euclidean and non-Euclidean…

机器学习 · 计算机科学 2024-11-11 Raef Bassily , Cristóbal Guzmán , Michael Menart

A major approach to saddle point optimization $\min_x\max_y f(x, y)$ is a gradient based approach as is popularized by generative adversarial networks (GANs). In contrast, we analyze an alternative approach relying only on an oracle that…

最优化与控制 · 数学 2021-04-02 Youhei Akimoto

In this paper, we study the gradient descent-ascent method for convex-concave saddle-point problems. We derive a new non-asymptotic global convergence rate in terms of distance to the solution set by using the semidefinite programming…

最优化与控制 · 数学 2022-09-19 Moslem Zamani , Hadi Abbaszadehpeivasti , Etienne de Klerk

The aim of this manuscript is to approach by means of first order differential equations/inclusions convex programming problems with two-block separable linear constraints and objectives, whereby (at least) one of the components of the…

最优化与控制 · 数学 2020-05-21 Sandy Bitterlich , Ernö Robert Csetnek , Gert Wanka

We consider the problem of finding critical points of functions that are non-convex and non-smooth. Studying a fairly broad class of such problems, we analyze the behavior of three gradient-based methods (gradient descent, proximal update,…

机器学习 · 统计学 2018-04-26 Koulik Khamaru , Martin J. Wainwright

We introduce a primal-dual stochastic gradient oracle method for distributed convex optimization problems over networks. We show that the proposed method is optimal in terms of communication steps. Additionally, we propose a new analysis…

最优化与控制 · 数学 2019-11-28 Darina Dvinskikh , Eduard Gorbunov , Alexander Gasnikov , Pavel Dvurechensky , Cesar A. Uribe

We derive stability criteria for saddle points of a class of nonsmooth optimization problems in Hilbert spaces arising in PDE-constrained optimization, using metric regularity of infinite-dimensional set-valued mappings. A main ingredient…

最优化与控制 · 数学 2017-02-13 Christian Clason , Tuomo Valkonen

By the asymptotic oracle property, non-convex penalties represented by minimax concave penalty (MCP) and smoothly clipped absolute deviation (SCAD) have attracted much attentions in high-dimensional data analysis, and have been widely used…

统计计算 · 统计学 2021-11-24 Peili Li , Min Liu , Zhou Yu

We study the online saddle point problem, an online learning problem where at each iteration a pair of actions need to be chosen without knowledge of the current and future (convex-concave) payoff functions. The objective is to minimize the…

机器学习 · 统计学 2020-04-07 Adrian Rivera , He Wang , Huan Xu

This paper studies a class of multiagent stochastic optimization problems where the objective is to minimize the expected value of a function which depends on a random variable. The probability distribution of the random variable is unknown…

最优化与控制 · 数学 2018-12-18 Ashish Cherukuri , Jorge Cortes

In this paper, we study the lower iteration complexity bounds for finding the saddle point of a strongly convex and strongly concave saddle point problem: $\min_x\max_yF(x,y)$. We restrict the classes of algorithms in our investigation to…

最优化与控制 · 数学 2021-06-22 Junyu Zhang , Mingyi Hong , Shuzhong Zhang

We address distributed learning problems, both nonconvex and convex, over undirected networks. In particular, we design a novel algorithm based on the distributed Alternating Direction Method of Multipliers (ADMM) to address the challenges…

机器学习 · 计算机科学 2026-03-23 Xiaoxing Ren , Nicola Bastianello , Karl H. Johansson , Thomas Parisini

We consider the decentralized convex optimization problem, where multiple agents must cooperatively minimize a cumulative objective function, with each local function expressible as an empirical average of data-dependent losses.…

最优化与控制 · 数学 2020-12-15 Ketan Rajawat , Chirag Kumar

Inspired by the Optimistic Gradient Ascent-Proximal Point Algorithm (OGAProx) proposed by Bo{\c{t}}, Csetnek, and Sedlmayer for solving a saddle-point problem associated with a convex-concave function with a nonsmooth coupling function and…

最优化与控制 · 数学 2023-11-01 Hui Ouyang

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…

机器学习 · 计算机科学 2022-01-20 An Xu , Zhouyuan Huo , Heng Huang

Distributed stochastic non-convex optimization problems have recently received attention due to the growing interest of signal processing, computer vision, and natural language processing communities in applications deployed over…

系统与控制 · 电气工程与系统科学 2024-10-14 Yiyue Chen , Abolfazl Hashemi , Haris Vikalo

The paper studies a distributed gradient descent (DGD) process and considers the problem of showing that in nonconvex optimization problems, DGD typically converges to local minima rather than saddle points. The paper considers…

最优化与控制 · 数学 2019-10-24 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

We develop a new consensus-based distributed algorithm for solving learning problems with feature partitioning and non-smooth convex objective functions. Such learning problems are not separable, i.e., the associated objective functions…

信号处理 · 电气工程与系统科学 2022-08-25 Cristiano Gratton , Naveen K. D. Venkategowda , Reza Arablouei , Stefan Werner

Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments.…

最优化与控制 · 数学 2019-07-04 Stefan Vlaski , Ali H. Sayed