中文
相关论文

相关论文: Accelerated Quasi-Newton Proximal Extragradient: F…

200 篇论文

In this paper, we propose a quasi-Newton method for solving smooth and monotone nonlinear equations, including unconstrained minimization and minimax optimization as special cases. For the strongly monotone setting, we establish two global…

最优化与控制 · 数学 2024-10-04 Ruichen Jiang , Aryan Mokhtari

In this paper, we investigate the convergence behavior of the Accelerated Newton Proximal Extragradient (A-NPE) method when employing inexact Hessian information. The exact A-NPE method was the pioneer near-optimal second-order approach,…

最优化与控制 · 数学 2024-02-20 Ziyu Huang , Bo Jiang , Yuntian Jiang

In [19], a general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed and a sublinear global convergence rate has been established. In this paper, we analyze the convergence properties…

数值分析 · 计算机科学 2017-10-18 Hiva Ghanbari , Katya Scheinberg

In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient of the smooth part of the objective function can only be…

最优化与控制 · 数学 2019-10-22 Minghan Yang , Andre Milzarek , Zaiwen Wen , Tong Zhang

Quasi-Newton methods are widely used for solving convex optimization problems due to their ease of implementation, practical efficiency, and strong local convergence guarantees. However, their global convergence is typically established…

Quasi-Newton algorithms are among the most popular iterative methods for solving unconstrained minimization problems, largely due to their favorable superlinear convergence property. However, existing results for these algorithms are…

最优化与控制 · 数学 2023-07-26 Ruichen Jiang , Qiujiang Jin , Aryan Mokhtari

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

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

机器学习 · 统计学 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

In this paper, we propose the first Quasi-Newton method with a global convergence rate of $O(k^{-1})$ for general convex functions. Quasi-Newton methods, such as BFGS, SR-1, are well-known for their impressive practical performance.…

最优化与控制 · 数学 2023-05-30 Dmitry Kamzolov , Klea Ziu , Artem Agafonov , Martin Takáč

Stochastic second-order methods achieve fast local convergence in strongly convex optimization by using noisy Hessian estimates to precondition the gradient. However, these methods typically reach superlinear convergence only when the…

最优化与控制 · 数学 2024-11-12 Ruichen Jiang , Michał Dereziński , Aryan Mokhtari

Recent studies incorporate Nesterov's accelerated gradient method for the acceleration of gradient based training. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown to drastically improve the convergence speed compared to the…

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

In this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerated $\mathcal{O}(1/k^2)$ last-iterate rates, faster than the…

最优化与控制 · 数学 2021-06-11 TaeHo Yoon , Ernest K. Ryu

We study the problem of finding an $\epsilon$-first-order stationary point (FOSP) of a smooth function, given access only to gradient information. The best-known gradient query complexity for this task, assuming both the gradient and…

最优化与控制 · 数学 2024-12-04 Ruichen Jiang , Aryan Mokhtari , Francisco Patitucci

Optimization problems with composite functions consist of an objective function which is the sum of a smooth and a (convex) nonsmooth term. This particular structure is exploited by the class of proximal gradient methods and some of their…

最优化与控制 · 数学 2022-10-17 Christian Kanzow , Theresa Lechner

Classical convergence analyses for optimization algorithms rely on the widely-adopted uniform smoothness assumption. However, recent experimental studies have demonstrated that many machine learning problems exhibit non-uniform smoothness,…

机器学习 · 计算机科学 2024-09-27 Zhenyu Sun , Ermin Wei

In this paper, we propose an inexact proximal Newton-type method for nonconvex composite problems. We establish the global convergence rate of the order $\mathcal{O}(k^{-1/2})$ in terms of the minimal norm of the KKT residual mapping and…

最优化与控制 · 数学 2024-12-26 Hong Zhu

This paper proposes a nonmonotone proximal quasi-Newton algorithm for unconstrained convex multiobjective composite optimization problems. To design the search direction, we minimize the max-scalarization of the variations of the Hessian…

最优化与控制 · 数学 2023-10-04 Xiaoxue Jiang

We propose an accelerated forward-backward method with fast convergence rate for finding a minimizer of a decomposable nonsmooth convex function over a closed convex set, and name it smoothing accelerated proximal gradient (SAPG) algorithm.…

最优化与控制 · 数学 2021-10-05 Wei Bian , Fan Wu

We analyze the convergence rate of the monotone accelerated proximal gradient method, which can be used to solve structured convex composite optimization problems. A linear convergence rate is established when the smooth part of the…

最优化与控制 · 数学 2026-03-16 Zepeng Wang , Juan Peypouquet

We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $\ell$-smoothness condition $||\nabla^{2}f(x)|| \le \ell\left(||\nabla f(x)||\right),$ which generalizes the $L$-smoothness…

最优化与控制 · 数学 2026-05-22 Alexander Tyurin
‹ 上一页 1 2 3 10 下一页 ›