基于凸共轭的一阶方法收敛性
最优化与控制
2017-07-31 v1
作者:
Javier Pena
摘要
本文给出了一种统一而简洁的方法,用于证明无约束凸最小化中子梯度、梯度和加速梯度方法的 O(1/k)、O(1/k) 和 O(1/k2) 收敛速率。在这三种情况下,收敛性的证明均源于由目标函数的凸共轭定义的通用界。
引用
@article{arxiv.1707.09084,
title = {Convergence of first-order methods via the convex conjugate},
author = {Javier Pena},
journal= {arXiv preprint arXiv:1707.09084},
year = {2017}
}
相关论文
查看更多相关论文 →
最优化与控制 · 数学
Convergence rates of proximal gradient methods via the convex conjugate
David H. Gutman, Javier F. Pena
2018-01-10
最优化与控制 · 数学
First-order algorithms converge faster than $O(1/k)$ on convex problems
Ching-pei Lee, Stephen J. Wright
2019-05-15
最优化与控制 · 数学
Convergence of Stochastic Proximal Gradient Algorithm
Lorenzo Rosasco, Silvia Villa, Bang Công Vũ
2016-08-11
最优化与控制 · 数学
Non-ergodic Complexity of Convex Proximal Inertial Gradient Descents
Tao Sun, Linbo Qiao, Dongsheng Li
2019-07-19
最优化与控制 · 数学
First order constrained optimization algorithms with feasibility updates
C. H. Jeffrey Pang
2015-06-30
最优化与控制 · 数学
General Convergence Rates Follow From Specialized Rates Assuming Growth Bounds
Benjamin Grimmer
2019-05-16
最优化与控制 · 数学
Convergence rates analysis of a multiobjective proximal gradient method
Hiroki Tanabe, Ellen H. Fukuda, Nobuo Yamashita
2022-04-11
最优化与控制 · 数学
Universal Complexity Bounds for Universal Gradient Methods in Nonlinear Optimization
Yurii Nesterov
2025-09-26
最优化与控制 · 数学
General convergence analysis of stochastic first order methods for composite optimization
Ion Necoara
2020-03-10
最优化与控制 · 数学
Linear convergence of first order methods for non-strongly convex optimization
I. Necoara, Yu. Nesterov, F. Glineur
2016-08-10
最优化与控制 · 数学
Gradient methods for convex minimization: better rates under weaker conditions
Hui Zhang, Wotao Yin
2013-09-10
最优化与控制 · 数学
Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity
Benjamin Grimmer
2018-02-28
最优化与控制 · 数学
Efficient First-order Methods for Convex Minimization: a Constructive Approach
Yoel Drori, Adrien B. Taylor
2019-06-27
最优化与控制 · 数学
Convergence analysis of approximate primal solutions in dual first-order methods
Jie Lu, Mikael Johansson
2015-02-24
最优化与控制 · 数学
Convergence Rate Analysis for Monotone Accelerated Proximal Gradient Method
Zepeng Wang, Juan Peypouquet
2026-03-16
数值分析 · 数学
Convergence rates for the stochastic gradient descent method for non-convex objective functions
Benjamin Fehrman, Benjamin Gess, Arnulf Jentzen
2021-11-02
最优化与控制 · 数学
A unified convergence bound for conjugate gradient and accelerated gradient
Sahar Karimi, Stephen A. Vavasis
2016-05-03
机器学习 · 统计学
On Matching Pursuit and Coordinate Descent
Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch +3
2019-06-03
最优化与控制 · 数学
Convergence Rates of Subgradient Methods for Quasi-convex Optimization Problems
Yaohua Hu, Jiawen Li, Carisa Kwok Wai Yu
2019-10-25
最优化与控制 · 数学
Optimizing the Efficiency of First-Order Methods for Decreasing the Gradient of Smooth Convex Functions
Donghwan Kim, Jeffrey A. Fessler
2020-10-28
最优化与控制 · 数学
On fast convergence rates for generalized conditional gradient methods with backtracking stepsize
Karl Kunisch, Daniel Walter
2021-10-01
最优化与控制 · 数学
A Simple Parallel Algorithm with an $O(1/t)$ Convergence Rate for General Convex Programs
Hao Yu, Michael J. Neely
2017-08-01
最优化与控制 · 数学
On the convergence analysis of the optimized gradient method
Donghwan Kim, Jeffrey A. Fessler
2019-06-14
最优化与控制 · 数学
Full Convergence of Regularized Methods for Unconstrained Optimization
Andrea Cristofari
2025-06-16
机器学习 · 计算机科学
Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent
Nicholas J. A. Harvey, Christopher Liaw, Sikander Randhawa
2019-09-04