Image de couverture de livre

Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rotaru, Teodor, Glineur, François, Patrinos, Panagiotis
Format:	Preprint
Publié:	2024
Sujets:	Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improved convergence rates for the Difference-of-Convex algorithm
par: Rotaru, Teodor, et autres
Publié: (2024)

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
par: Rotaru, Teodor, et autres
Publié: (2025)

Tight Convergence Rates in Gradient Mapping for the Difference-of-Convex Algorithm
par: Rotaru, Teodor, et autres
Publié: (2025)

Worst-case convergence analysis of relatively inexact gradient descent on smooth convex functions
par: Vernimmen, Pierre, et autres
Publié: (2025)

Analytic analysis of the worst-case complexity of the gradient method with exact line search and the Polyak stepsize
par: Huang, Ya-Kui, et autres
Publié: (2024)

Exact Convergence rate of the subgradient method by using Polyak step size
par: Zamani, Moslem, et autres
Publié: (2024)

Global and local approaches for the minimization of a sum of pointwise minima of convex functions
par: Van Dessel, Guillaume, et autres
Publié: (2025)

Exact worst-case convergence rates for Douglas--Rachford and Davis--Yin splitting methods
par: Nguyen, Edward Duc Hien, et autres
Publié: (2025)

Nonlinear conjugate gradient methods: worst-case convergence rates via computer-assisted analyses
par: Gupta, Shuvomoy Das, et autres
Publié: (2023)

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
par: Bodard, Alexander, et autres
Publié: (2025)

Empirical and computer-aided robustness analysis of long-step and accelerated methods in smooth convex optimization
par: Vernimmen, Pierre, et autres
Publié: (2025)

Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes
par: Lan, Guanghui, et autres
Publié: (2024)

On the convergence of proximal gradient methods for convex simple bilevel optimization
par: Latafat, Puya, et autres
Publié: (2023)

Presolve techniques for quasi-convex chance constraints with finite-support low-dimensional uncertainty
par: Van Dessel, Guillaume, et autres
Publié: (2025)

Forward-backward splitting under the light of generalized convexity
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

On the convergence analysis of the decentralized projected gradient descent method
par: Choi, Woocheol, et autres
Publié: (2023)

The inexact power augmented Lagrangian method for constrained nonconvex optimization
par: Bodard, Alexander, et autres
Publié: (2024)

Dualities for non-Euclidean smoothness and strong convexity under the light of generalized conjugacy
par: Laude, Emanuel, et autres
Publié: (2021)

On the convergence result of the gradient-push algorithm on directed graphs with constant stepsize
par: Choi, Woocheol, et autres
Publié: (2023)

Proximal gradient methods with inexact oracle of degree q for composite optimization
par: Nabou, Yassine, et autres
Publié: (2024)

Global minimization of a minimum of a finite collection of functions
par: Van Dessel, Guillaume, et autres
Publié: (2024)

Global minimisation of nonconvex functions by generalising the mirror descent method
par: Millán, Reinier Díaz, et autres
Publié: (2024)

Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
par: Latafat, Puya, et autres
Publié: (2019)

A unified framework for inexact adaptive stepsizes in the gradient methods, the conjugate gradient methods and the quasi-Newton methods for strictly convex quadratic optimization
par: Liu, Zexian
Publié: (2026)

PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
par: Goujaud, Baptiste, et autres
Publié: (2022)

A consensus-based optimization method for nonsmooth nonconvex programs with approximated gradient descent scheme
par: Wei, Jiazhen, et autres
Publié: (2025)

On convergence rates of subgradient descent on semialgebraic functions
par: Chzhen, Evgenii, et autres
Publié: (2026)

Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization
par: Lan, Guanghui, et autres
Publié: (2023)

Long-time dynamics and universality of nonconvex gradient descent
par: Han, Qiyang
Publié: (2025)

A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima
par: Ahookhosh, Masoud, et autres
Publié: (2019)

Nonlinearly preconditioned gradient flows
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
par: Bodard, Alexander, et autres
Publié: (2025)

Anisotropic Proximal Point Algorithm
par: Laude, Emanuel, et autres
Publié: (2023)

Anisotropic Proximal Gradient
par: Laude, Emanuel, et autres
Publié: (2022)

Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach
par: Bodard, Alexander, et autres
Publié: (2026)

Dual first-order methods for efficient computation of convex hull prices
par: Tanji, Sofiane, et autres
Publié: (2025)

Proximal gradient-type method with generalized distance and convergence analysis without global descent lemma
par: Yagishita, Shotaro, et autres
Publié: (2025)

Nonconvex optimization and convergence of stochastic gradient descent, and solution of asynchronous game
par: Buck, Kevin, et autres
Publié: (2025)

A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity
par: Davis, Damek, et autres
Publié: (2026)

Bregman Finito/MISO for nonconvex regularized finite sum minimization without Lipschitz gradient continuity
par: Latafat, Puya, et autres
Publié: (2021)