中文
相关论文

相关论文: A Unified Convergence Analysis of First Order Conv…

200 篇论文

Recent work on high-resolution ordinary differential equations (HR-ODEs) captures fine nuances among different momentum-based optimization methods, leading to accurate theoretical insights. However, these HR-ODEs often appear disconnected,…

最优化与控制 · 数学 2025-03-20 Hoomaan Maskan , Konstantinos C. Zygalakis , Armin Eftekhari , Alp Yurtsever

Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restricted strong…

机器学习 · 计算机科学 2024-01-08 Fangshuo Liao , Anastasios Kyrillidis

We present two classes of differentially private optimization algorithms derived from the well-known accelerated first-order methods. The first algorithm is inspired by Polyak's heavy ball method and employs a smoothing approach to decrease…

机器学习 · 计算机科学 2022-05-17 Nurdan Kuru , Ş. İlker Birbil , Mert Gurbuzbalaban , Sinan Yildirim

We present a methodology for establishing the existence of quadratic Lyapunov inequalities for a wide range of first-order methods used to solve convex optimization problems. In particular, we consider i) classes of optimization problems of…

最优化与控制 · 数学 2025-10-24 Manu Upadhyaya , Sebastian Banert , Adrien B. Taylor , Pontus Giselsson

We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal…

最优化与控制 · 数学 2016-07-05 Quoc Tran-Dinh

Despite their frequent slow convergence, proximal gradient schemes are widely used in large-scale optimization tasks due to their tremendous stability, scalability, and ease of computation. In this paper, we develop and investigate a…

统计计算 · 统计学 2025-08-19 Nicholas C. Henderson , Ravi Varadhan

Accelerated first order methods, also called fast gradient methods, are popular optimization methods in the field of convex optimization. However, they are prone to suffer from oscillatory behaviour that slows their convergence when medium…

最优化与控制 · 数学 2022-01-28 Teodoro Alamo , Pablo Krupa , Daniel Limon

We introduce a generic scheme for accelerating gradient-based optimization methods in the sense of Nesterov. The approach, called Catalyst, builds upon the inexact accelerated proximal point algorithm for minimizing a convex objective…

机器学习 · 统计学 2018-06-20 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime. Classical analyses…

最优化与控制 · 数学 2026-05-12 Don Li , Dacian Daescu

This paper considers a general convex constrained problem setting where functions are not assumed to be differentiable nor Lipschitz continuous. Our motivation is in finding a simple first-order method for solving a wide range of convex…

最优化与控制 · 数学 2021-03-19 Michael R. Metel , Akiko Takeda

We propose first order algorithms for convex optimization problems where the feasible set is described by a large number of convex inequalities that is to be explored by subgradient projections. The first algorithm is an adaptation of a…

最优化与控制 · 数学 2015-06-30 C. H. Jeffrey Pang

We consider unconstrained minimization of smooth convex functions. We propose a novel variational perspective using forced Euler-Lagrange equation that allows for studying high-resolution ODEs. Through this, we obtain a faster convergence…

最优化与控制 · 数学 2023-11-06 Hoomaan Maskan , Konstantinos C. Zygalakis , Alp Yurtsever

We investigate the integration of Nesterov-type acceleration into primal-dual methods for structured convex optimization. While proximal splitting algorithms efficiently handle composite problems of the form $\min_x f(x)+g(x)+h(Kx)$,…

最优化与控制 · 数学 2026-04-13 Laurent Condat , Abdurakhmon Sadiev , Peter Richtárik

We study the robustness of accelerated first-order algorithms to stochastic uncertainties in gradient evaluation. Specifically, for unconstrained, smooth, strongly convex optimization problems, we examine the mean-squared error in the…

最优化与控制 · 数学 2020-02-21 Hesameddin Mohammadi , Meisam Razaviyayn , Mihailo R. Jovanović

We study nonsmooth convex minimization through a continuous-time dynamical system that can be seen as a high-resolution ODE of Nesterov Accelerated Gradient (NAG) adapted to the nonsmooth case. We apply a time-varying Moreau envelope…

最优化与控制 · 数学 2026-03-27 Manh Hung Le , Andrea Simonetto

In this paper, we generalize the well-known Nesterov's accelerated gradient (AG) method, originally designed for convex smooth optimization, to solve nonconvex and possibly stochastic optimization problems. We demonstrate that by properly…

最优化与控制 · 数学 2013-10-15 Saeed Ghadimi , Guanghui Lan

By time discretization of a second-order primal-dual dynamical system with damping $\alpha/t$ where an inertial construction in the sense of Nesterov is needed only for the primal variable, we propose a fast primal-dual algorithm for a…

最优化与控制 · 数学 2022-06-06 Xin He , Rong Hu , Ya-Ping Fang

Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we propose a stochastic (online) quasi-Newton method with…

机器学习 · 计算机科学 2020-10-16 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai

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

There are much recent interests in solving noncovnex min-max optimization problems due to its broad applications in many areas including machine learning, networked resource allocations, and distributed optimization. Perhaps, the most…

最优化与控制 · 数学 2021-12-20 Thinh T. Doan