An optimal gradient method for smooth strongly convex minimization

被引：0
|
作者：
Adrien Taylor
Yoel Drori
机构：
[1] PSL Research University,INRIA, Département d’informatique de l’ENS, École normale supérieure, CNRS
[2] Google Research Israel,undefined
来源：
Mathematical Programming | 2023年 / 199卷
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
We present an optimal gradient method for smooth strongly convex optimization. The method is optimal in the sense that its worst-case bound on the distance to an optimal point exactly matches the lower bound on the oracle complexity for the class of problems, meaning that no black-box first-order method can have a better worst-case guarantee without further assumptions on the class of problems at hand. In addition, we provide a constructive recipe for obtaining the algorithmic parameters of the method and illustrate that it can be used for deriving methods for other optimality criteria as well.
引用
收藏
页码：557 / 594
页数：37
相关论文
共 50 条
  • [21] Convergence of the gradient projection method for generalized convex minimization
    Wang, CY
    Xiu, NH
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2000, 16 (02) : 111 - 120
  • [22] A STRONGLY CONVERGENT METHOD FOR NONSMOOTH CONVEX MINIMIZATION IN HILBERT SPACES
    Bello Cruz, J. Y.
    Iusem, A. N.
    NUMERICAL FUNCTIONAL ANALYSIS AND OPTIMIZATION, 2011, 32 (10) : 1009 - 1018
  • [23] Accelerated Distributed Nesterov Gradient Descent for Smooth and Strongly Convex Functions
    Qu, Guannan
    Li, Na
    2016 54TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2016, : 209 - 216
  • [24] On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions
    Etienne de Klerk
    François Glineur
    Adrien B. Taylor
    Optimization Letters, 2017, 11 : 1185 - 1199
  • [25] On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions
    de Klerk, Etienne
    Glineur, Francois
    Taylor, Adrien B.
    OPTIMIZATION LETTERS, 2017, 11 (07) : 1185 - 1199
  • [26] The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization
    Kovalev, Dmitry
    Gasnikov, Alexander
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [27] Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal Transport
    Paty, Francois-Pierre
    d'Aspremont, Alexandre
    Cuturi, Marco
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 1222 - 1231
  • [28] A VARIANT OF THE PROXIMAL GRADIENT METHOD FOR CONSTRAINED CONVEX MINIMIZATION PROBLEMS
    Kesornprom, Suparat
    Kankam, Kunrada
    Inkrong, Papatsara
    Pholasa, Nattawut
    Cholamjiak, Prasit
    JOURNAL OF NONLINEAR FUNCTIONAL ANALYSIS, 2024, 2024
  • [29] A delayed weighted gradient method for strictly convex quadratic minimization
    Harry Fernando Oviedo Leon
    Computational Optimization and Applications, 2019, 74 : 729 - 746
  • [30] A delayed weighted gradient method for strictly convex quadratic minimization
    Oviedo Leon, Harry Fernando
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2019, 74 (03) : 729 - 746
12345