中文
相关论文

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

200 篇论文

When training neural networks with low-precision computation, rounding errors often cause stagnation or are detrimental to the convergence of the optimizers; in this paper we study the influence of rounding errors on the convergence of the…

机器学习 · 统计学 2025-01-22 Lu Xia , Michiel E. Hochstenbach , Stefano Massei

In this paper we consider a stochastic heavy-ball method for solving linear ill-posed inverse problems. With suitable choices of the step-sizes and the momentum coefficients, we establish the regularization property of the method under {\it…

数值分析 · 数学 2024-06-25 Qinian Jin , Yanjun Liu

We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient…

机器学习 · 计算机科学 2018-10-26 Lin F. Yang , R. Arora , V. Braverman , Tuo Zhao

In this work, we establish the linear convergence estimate for the gradient descent involving the delay $\tau\in\mathbb{N}$ when the cost function is $\mu$-strongly convex and $L$-smooth. This result improves upon the well-known estimates…

最优化与控制 · 数学 2024-02-23 Hyung Jun Choi , Woocheol Choi , Jinmyoung Seok

This paper is devoted to the investigation of inertial dynamical systems with implicit Hessian-driven damping for strongly quasiconvex optimization which is a specific class of nonconvex optimization problems. We first establish exponential…

最优化与控制 · 数学 2026-02-27 Zeying Gao , Xiangkai Sun , Liang He

In this paper, we revisit a classical adaptive stepsize strategy for gradient descent: the Polyak stepsize (PolyakGD), originally proposed in Polyak (1969). We study the convergence behavior of PolyakGD from two perspectives: tight…

最优化与控制 · 数学 2026-03-10 Chang He , Wenzhi Gao , Bo Jiang , Madeleine Udell , Shuzhong Zhang

We present a unified convergence analysis for first order convex optimization methods using the concept of strong Lyapunov conditions. Combining this with suitable time scaling factors, we are able to handle both convex and strong convex…

最优化与控制 · 数学 2021-08-03 Long Chen , Hao Luo

Heavy-ball momentum with decaying learning rates is widely used with SGD for optimizing deep learning models. In contrast to its empirical popularity, the understanding of its theoretical property is still quite limited, especially under…

机器学习 · 计算机科学 2024-03-19 Rui Pan , Yuxing Liu , Xiaoyu Wang , Tong Zhang

Due to its applications in many different places in machine learning and other connected engineering applications, the problem of minimization of a smooth function that satisfies the Polyak-{\L}ojasiewicz condition receives much attention…

最优化与控制 · 数学 2022-12-09 Ilya A. Kuruzov , Fedor S. Stonyakin , Mohammad S. Alkousa

Bilevel optimization is widely applied in many machine learning tasks such as hyper-parameter learning, meta learning and reinforcement learning. Although many algorithms recently have been developed to solve the bilevel optimization…

最优化与控制 · 数学 2024-07-26 Feihu Huang

We give new characterizations of growth conditions at strict local minimizers. The main characterizations are a variant of the so-called tilt stability property and an analog of the classical Polyak--\L{}ojasiewicz condition, where the…

最优化与控制 · 数学 2026-02-11 Alberto Domínguez Corella , Trí Minh Lê

In this paper we consider ill-posed inverse problems, both linear and nonlinear, by a heavy ball method in which a strongly convex regularization function is incorporated to detect the feature of the sought solution. We develop ideas on how…

数值分析 · 数学 2024-04-05 Qinian Jin , Qin Huang

Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more complex due to the interaction between different players and is…

最优化与控制 · 数学 2021-01-27 Guodong Zhang , Yuanhao Wang

In this work, we consider a continuous dynamical system associated with the fixed point set of a nonexpansive operator which was originally studied by Bo\c{t} & Csetnek (2015). Our main results establish convergence rates for the system's…

最优化与控制 · 数学 2021-06-09 Ernö Robert Csetnek , Andrew Eberhard , Matthew K. Tam

We study differentiable strongly quasiconvex functions for providing new properties for algorithmic and monotonicity purposes. Furthemore, we provide insights into the decreasing behaviour of strongly quasiconvex functions, applying this…

最优化与控制 · 数学 2024-10-07 Felipe Lara , Raúl T. Marcavillaca , Phan T. Vuong

We analyze the complexity of biased stochastic gradient methods (SGD), where individual updates are corrupted by deterministic, i.e. biased error terms. We derive convergence results for smooth (non-convex) functions and give improved rates…

机器学习 · 计算机科学 2021-05-11 Ahmad Ajalloeian , Sebastian U. Stich

Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order…

最优化与控制 · 数学 2020-12-25 Guilherme França , Jeremias Sulam , Daniel P. Robinson , René Vidal

In large-scale learning algorithms, the momentum term is usually included in the stochastic sub-gradient method to improve the learning speed because it can navigate ravines efficiently to reach a local minimum. However, step-size and…

机器学习 · 计算机科学 2024-08-07 Wen-Liang Hwang

The heavy-ball momentum method accelerates gradient descent with a momentum term but lacks accelerated convergence for general smooth strongly convex problems. This work introduces the Accelerated Over-Relaxation Heavy-Ball (AOR-HB) method,…

最优化与控制 · 数学 2025-02-18 Jingrong Wei , Long Chen

We study the convergence rate of gradient-based local search methods for solving low-rank matrix recovery problems with general objectives in both symmetric and asymmetric cases, under the assumption of the restricted isometry property.…

最优化与控制 · 数学 2022-03-10 Yingjie Bi , Haixiang Zhang , Javad Lavaei