中文
相关论文

相关论文: Convergence rates for the Heavy-Ball continuous dy…

200 篇论文

In this paper, we examine the convergence properties of heavy-ball dynamics with Hessian-driven damping in smooth non-convex optimization problems satisfying a {\L}ojasiewicz condition. In this general setting, we provide a series of tight,…

最优化与控制 · 数学 2025-06-16 Vassilis Apidopoulos , Vasiliki Mavrogeorgou , Theodoros G. Tsironis

In this paper we study a second order dynamical system with variable coefficients in connection to the minimization problem of a smooth nonconvex function. The convergence of the trajectories generated by the dynamical system to a critical…

最优化与控制 · 数学 2025-10-21 Szilárd Csaba László

In this work, we analyze the convergence of Polyak's heavy ball method in both continuous and discrete time for non-convex $C^4$-objective functions satisfying the Polyak-Lojasiewicz inequality. Under this weak assumption, we recover the…

最优化与控制 · 数学 2026-02-03 Sebastian Kassing , Simon Weissmann

In this paper, we derive a new linear convergence rate for the gradient method with fixed step lengths for non-convex smooth optimization problems satisfying the Polyak-Lojasiewicz (PL) inequality. We establish that the PL inequality is a…

最优化与控制 · 数学 2022-04-05 Hadi Abbaszadehpeivasti , Etienne de Klerk , Moslem Zamani

In this paper, we investigate the growth error bound condition. By using the proximal point algorithm, we first provide a more accessible and elementary proof of the fact that Kurdyka-{\L}ojasiewicz conditions imply growth error bound…

最优化与控制 · 数学 2024-06-12 Qinian Jin

Heavy Ball (HB) nowadays is one of the most popular momentum methods in non-convex optimization. It has been widely observed that incorporating the Heavy Ball dynamic in gradient-based methods accelerates the training process of modern…

最优化与控制 · 数学 2023-08-30 Jun-Kun Wang , Chi-Heng Lin , Andre Wibisono , Bin Hu

This paper addresses smooth convexly constrained optimization problems where the Euclidean projection onto the feasible set is computationally tractable. Although momentum techniques like Polyak's heavy-ball are known for accelerating…

最优化与控制 · 数学 2026-03-20 Federica Donnini , Pierluigi Mansueto

Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary…

机器学习 · 计算机科学 2025-05-15 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a…

最优化与控制 · 数学 2024-06-04 Wouter Jongeneel , Daniel Kuhn , Mengmeng Li

We study the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system combining asymptotic vanishing viscous and Hessian-driven damping. We establish a fast sublinear convergence…

最优化与控制 · 数学 2025-07-18 Zepeng Wang , Juan Peypouquet

Communication delays and synchronization are major bottlenecks for parallel computing, and tolerating asynchrony is therefore crucial for accelerating parallel computation. Motivated by optimization problems that do not satisfy convexity…

最优化与控制 · 数学 2021-05-25 Kasra Yazdani , Matthew Hale

This paper focuses on stochastic methods for solving smooth non-convex strongly-concave min-max problems, which have received increasing attention due to their potential applications in deep learning (e.g., deep AUC maximization,…

机器学习 · 计算机科学 2023-04-19 Zhishuai Guo , Yan Yan , Zhuoning Yuan , Tianbao Yang

In this paper, we revisit the convergence of the Heavy-ball method, and present improved convergence complexity results in the convex setting. We provide the first non-ergodic O(1/k) rate result of the Heavy-ball algorithm with constant…

最优化与控制 · 数学 2018-11-12 Tao Sun , Penghang Yin , Dongsheng Li , Chun Huang , Lei Guan , Hao Jiang

Momentum methods for convex optimization often rely on precise choices of algorithmic parameters, based on knowledge of problem parameters, in order to achieve fast convergence, as well as to prevent oscillations that could severely…

系统与控制 · 电气工程与系统科学 2021-03-24 Justin H. Le , Andrew R. Teel

The Heavy Ball Method, proposed by Polyak over five decades ago, is a first-order method for optimizing continuous functions. While its stochastic counterpart has proven extremely popular in training deep networks, there are almost no known…

机器学习 · 计算机科学 2021-02-16 Jun-Kun Wang , Jacob Abernethy

We investigate the asymptotic properties of the trajectories generated by a second-order dynamical system of proximal-gradient type stated in connection with the minimization of the sum of a nonsmooth convex and a (possibly nonconvex)…

最优化与控制 · 数学 2017-11-20 Radu Ioan Bot , Ernö Robert Csetnek , Szilárd Csaba László

In this short note, we consider the problem of solving a min-max zero-sum game. This problem has been extensively studied in the convex-concave regime where the global solution can be computed efficiently. Recently, there have also been…

最优化与控制 · 数学 2018-12-11 Maziar Sanjabi , Meisam Razaviyayn , Jason D. Lee

When considering the minimization of a quadratic or strongly convex function, it is well known that first-order methods involving an inertial term weighted by a constant-in-time parameter are particularly efficient (see Polyak [32],…

最优化与控制 · 数学 2025-01-17 Jean-François Aujol , Charles Dossal , Hippolyte Labarrière , Aude Rondepierre

In this work, we propose an adaptive variation on the classical Heavy-ball method for convex quadratic minimization. The adaptivity crucially relies on so-called "Polyak step-sizes", which consists in using the knowledge of the optimal…

最优化与控制 · 数学 2022-10-13 Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut

This paper deals with a natural stochastic optimization procedure derived from the so-called Heavy-ball method differential equation, which was introduced by Polyak in the 1960s with his seminal contribution [Pol64]. The Heavy-ball method…

统计理论 · 数学 2016-10-24 Sébastien Gadat , Fabien Panloup , Sofiane Saadane
‹ 上一页 1 2 3 10 下一页 ›