中文
相关论文

相关论文: A Saddle Point Remedy: Power of Variable Eliminati…

200 篇论文

Nonconvex optimization algorithms with random initialization have attracted increasing attention recently. It has been showed that many first-order methods always avoid saddle points with random starting points. In this paper, we answer a…

最优化与控制 · 数学 2019-07-24 Tao Sun , Dongsheng Li , Zhe Quan , Hao Jiang , Shengguo Li , Yong Dou

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

Many modern machine learning applications - from online principal component analysis to covariance matrix identification and dictionary learning - can be formulated as minimization problems on Riemannian manifolds, and are typically solved…

最优化与控制 · 数学 2023-11-07 Ya-Ping Hsieh , Mohammad Reza Karimi , Andreas Krause , Panayotis Mertikopoulos

Optimization of frame structures is formulated as a~non-convex optimization problem, which is currently solved to local optimality. In this contribution, we investigate four optimization approaches: (i) general non-linear optimization, (ii)…

最优化与控制 · 数学 2019-09-17 Marek Tyburec , Jan Zeman , Martin Kružík , Didier Henrion

Motivated by variational models in continuum mechanics, we introduce a novel algorithm to perform nonsmooth and nonconvex minimizations with linear constraints in Euclidean spaces. We show how this algorithm is actually a natural…

偏微分方程分析 · 数学 2015-03-20 Marco Artina , Massimo Fornasier , Francesco Solombrino

In this paper, we design an inertial accelerated primal-dual algorithm to address the convex-concave saddle point problem, which is formulated as $\min_{x}\max_{y} f(x) + \langle Kx, y \rangle - g(y)$. Remarkably, both functions $f$ and $g$…

最优化与控制 · 数学 2024-04-17 X. He , N. J. Huang , Y. P. Fang

Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point…

最优化与控制 · 数学 2019-12-05 Abhishek Roy , Yifang Chen , Krishnakumar Balasubramanian , Prasant Mohapatra

We consider empirical risk minimization of linear predictors with convex loss functions. Such problems can be reformulated as convex-concave saddle point problems, and thus are well suitable for primal-dual first-order algorithms. However,…

最优化与控制 · 数学 2017-03-09 Jialei Wang , Lin Xiao

This paper considers the minimization of a general objective function $f(X)$ over the set of rectangular $n\times m$ matrices that have rank at most $r$. To reduce the computational burden, we factorize the variable $X$ into a product of…

信息论 · 计算机科学 2018-07-04 Zhihui Zhu , Qiuwei Li , Gongguo Tang , Michael B. Wakin

In this work, we consider strongly convex strongly concave (SCSC) saddle point (SP) problems $\min_{x\in\mathbb{R}^{d_x}}\max_{y\in\mathbb{R}^{d_y}}f(x,y)$ where $f$ is $L$-smooth, $f(.,y)$ is $\mu$-strongly convex for every $y$, and…

最优化与控制 · 数学 2022-02-22 Bugra Can , Mert Gurbuzbalaban , Necdet Serhat Aybat

Large-scale non-convex optimization problems are expensive to solve due to computational and memory costs. To reduce the costs, first-order (computationally efficient) and asynchronous-parallel (memory efficient) algorithms are necessary to…

最优化与控制 · 数学 2022-11-21 Marco Bornstein , Jin-Peng Liu , Jingling Li , Furong Huang

We propose perturbed proximal algorithms that can provably escape strict saddles for nonsmooth weakly convex functions. The main results are based on a novel characterization of $\epsilon$-approximate local minimum for nonsmooth functions,…

机器学习 · 计算机科学 2025-07-22 Minhui Huang , Weiming Zhu

We present a non-convex optimization algorithm metaheuristic, based on the training of a deep generative network, which enables effective searching within continuous, ultra-high dimensional landscapes. During network training, populations…

机器学习 · 计算机科学 2023-07-11 Jiaqi Jiang , Jonathan A. Fan

Momentum Stochastic Gradient Descent (MSGD) algorithm has been widely applied to many nonconvex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian inference, and etc. Despite its empirical…

机器学习 · 计算机科学 2021-03-09 Tianyi Liu , Zhehui Chen , Enlu Zhou , Tuo Zhao

This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a curvilinear linesearch method. These developments are…

最优化与控制 · 数学 2025-06-30 Alexander Bodard , Masoud Ahookhosh , Panagiotis Patrinos

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

We develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive application of linear…

最优化与控制 · 数学 2015-03-25 Yossi Arjevani , Shai Shalev-Shwartz , Ohad Shamir

In the paper, we develop a composite version of Mirror Prox algorithm for solving convex-concave saddle point problems and monotone variational inequalities of special structure, allowing to cover saddle point/variational analogies of what…

最优化与控制 · 数学 2014-05-23 Niao He , Anatoli Juditsky , Arkadi Nemirovski

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…

In the paper, we generalize the approach Gasnikov et. al, 2017, which allows to solve (stochastic) convex optimization problems with an inexact gradient-free oracle, to the convex-concave saddle-point problem. The proposed approach works,…

最优化与控制 · 数学 2022-09-13 Aleksandr Beznosikov , Abdurakhmon Sadiev , Alexander Gasnikov