中文
相关论文

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

200 篇论文

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

最优化与控制 · 数学 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it difficult for gradient-based optimizers to converge to the global optimum.…

机器学习 · 计算机科学 2026-02-12 Tianqi Shen , Jinji Yang , Junze He , Kunhan Gao , Ziye Ma

We propose a regularized saddle-point algorithm for convex networked optimization problems with resource allocation constraints. Standard distributed gradient methods suffer from slow convergence and require excessive communication when…

系统与控制 · 计算机科学 2012-08-16 Andrea Simonetto , Tamas Keviczky , Mikael Johansson

In this work, we analyze the global convergence property of coordinate gradient descent with random choice of coordinates and stepsizes for non-convex optimization problems. Under generic assumptions, we prove that the algorithm iterate…

最优化与控制 · 数学 2022-12-01 Ziang Chen , Yingzhou Li , Jianfeng Lu

Using convex combination and linesearch techniques, we introduce a novel primal-dual algorithm for solving structured convex-concave saddle point problems with a generic smooth nonbilinear coupling term. Our adaptive linesearch strategy…

最优化与控制 · 数学 2024-01-17 Xiaokai Chang , Junfeng Yang , Hongchao Zhang

Gradient-related first-order methods have become the workhorse of large-scale numerical optimization problems. Many of these problems involve nonconvex objective functions with multiple saddle points, which necessitates an understanding of…

最优化与控制 · 数学 2022-03-10 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa

We study the optimization landscape and the stability properties of training problems with squared loss for neural networks and general nonlinear conic approximation schemes. It is demonstrated that, if a nonlinear conic approximation…

最优化与控制 · 数学 2021-12-03 Constantin Christof

We develop stochastic first-order primal-dual algorithms to solve a class of convex-concave saddle-point problems. When the saddle function is strongly convex in the primal variable, we develop the first stochastic restart scheme for this…

最优化与控制 · 数学 2021-04-13 Renbo Zhao

Constrained non-convex optimization is fundamentally challenging, as global solutions are generally intractable and constraint qualifications may not hold. However, in many applications, including safe policy optimization in control and…

最优化与控制 · 数学 2025-11-14 Ilyas Fatkhullin , Niao He , Guanghui Lan , Florian Wolf

This paper focuses on the distributed optimization of stochastic saddle point problems. The first part of the paper is devoted to lower bounds for the centralized and decentralized distributed methods for smooth (strongly) convex-(strongly)…

机器学习 · 计算机科学 2025-04-28 Aleksandr Beznosikov , Valentin Samokhin , Alexander Gasnikov

In this paper, we present novel randomized algorithms for solving saddle point problems whose dual feasible region is given by the direct product of many convex sets. Our algorithms can achieve an ${\cal O}(1/N)$ and ${\cal O}(1/N^2)$ rate…

最优化与控制 · 数学 2015-11-16 Cong Dang , Guanghui Lan

A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored. We analyze this heuristic…

机器学习 · 计算机科学 2016-11-22 Kfir Y. Levy

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical…

机器学习 · 计算机科学 2023-10-24 Mayank Baranwal , Param Budhraja , Vishal Raj , Ashish R. Hota

Two optimization algorithms are proposed for solving a stochastic programming problem for which the objective function is given in the form of the expectation of convex functions and the constraint set is defined by the intersection of…

最优化与控制 · 数学 2017-10-09 Hideaki Iiduka

There is a recent surge of interest in nonconvex reformulations via low-rank factorization for stochastic convex semidefinite optimization problem in the purpose of efficiency and scalability. Compared with the original convex formulations,…

最优化与控制 · 数学 2018-02-27 Jinshan Zeng , Ke Ma , Yuan Yao

This paper considers continuous-time coordination algorithms for networks of agents that seek to collectively solve a general class of nonsmooth convex optimization problems with an inherent distributed structure. Our algorithm design…

最优化与控制 · 数学 2017-05-17 Simon K. Niederländer , Jorge Cortés

We study non-smooth stochastic decentralized optimization problems over time-varying networks, where objective functions are distributed across nodes and network connections may intermittently appear or break. Specifically, we consider two…

最优化与控制 · 数学 2026-04-28 Maxim Divilkovskiy , Alexander Gasnikov

Non-smooth optimization is a core ingredient of many imaging or machine learning pipelines. Non-smoothness encodes structural constraints on the solutions, such as sparsity, group sparsity, low-rank and sharp edges. It is also the basis for…

最优化与控制 · 数学 2022-05-04 Clarice Poon , Gabriel Peyré

The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the…

最优化与控制 · 数学 2021-08-11 Meisam Razaviyayn , Tianjian Huang , Songtao Lu , Maher Nouiehed , Maziar Sanjabi , Mingyi Hong

We consider the population Wasserstein barycenter problem for random probability measures supported on a finite set of points and generated by an online stream of data. This leads to a complicated stochastic optimization problem where the…

最优化与控制 · 数学 2021-12-06 Daniil Tiapkin , Alexander Gasnikov , Pavel Dvurechensky